# gateway

A gateway is an intermediate system connecting two or more computer networks and enabling communication between them; in Internet documentation, it is an IP-level router.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Software-Defined Internet Integration of Satellite Networks (SDISN)

DevFeed: [Software-Defined Internet Integration of Satellite Networks (SDISN)](<https://devfeed.tech/articles/software-defined-internet-integration-of-satellite-networks-sdisn-146148.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25837>)

Author: Michael Menth, Moritz Fl\\"uchter, Jens Haala

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Networking](<https://devfeed.tech/sources/arxiv-networking.md>)

Topics: [Software-defined networking](<https://devfeed.tech/topics/sdn.md>), [routing-system](<https://devfeed.tech/topics/routing-system.md>), [gateway](<https://devfeed.tech/topics/gateway.md>), [Internet](<https://devfeed.tech/topics/internet.md>), [network security](<https://devfeed.tech/topics/network-security.md>)

Tags: [architecture](<https://devfeed.tech/tags/architecture.md>), [communication](<https://devfeed.tech/tags/communication.md>), [controller](<https://devfeed.tech/tags/controller.md>), [cs-ni](<https://devfeed.tech/tags/cs-ni.md>), [gateways](<https://devfeed.tech/tags/gateways.md>), [integration](<https://devfeed.tech/tags/integration.md>), [internet](<https://devfeed.tech/tags/internet.md>), [ip](<https://devfeed.tech/tags/ip.md>), [latency](<https://devfeed.tech/tags/latency.md>), [links](<https://devfeed.tech/tags/links.md>), [network](<https://devfeed.tech/tags/network.md>), [network-design](<https://devfeed.tech/tags/network-design.md>), [networks](<https://devfeed.tech/tags/networks.md>), [orbit](<https://devfeed.tech/tags/orbit.md>), [routing](<https://devfeed.tech/tags/routing.md>), [satellite](<https://devfeed.tech/tags/satellite.md>), [satellites](<https://devfeed.tech/tags/satellites.md>), [security](<https://devfeed.tech/tags/security.md>), [serving](<https://devfeed.tech/tags/serving.md>), [software](<https://devfeed.tech/tags/software.md>), [solution](<https://devfeed.tech/tags/solution.md>)

### AI overview

SDISN addresses changing reachability as user terminals (UTs) and gateways (GWs) switch serving satellites in a fast-moving constellation. GWs and serving satellites encapsulate traffic with forwarding information, which a controller continually updates to reflect serving-satellite changes and possible topology changes. The design aims to keep satellite complexity low, enable traffic engineering, and leave UTs outside the routing system. Proposed extensions support UTs whose traffic must stay within the constellation, and reduce latency from triangle routing through a fixed Home GW when a UT roams. UTs can instead receive dynamic IP addresses from a nearby GW/PoP as they roam. Traffic engineering can use alternate GWs and serving satellites.

### Source excerpt

arXiv:2611.25837v1 Announce Type: new Abstract: This paper proposes SDISN, a software-defined Internet integration of satellite networks. It facilitates the transmission of IP traffic from user terminals (UTs) or Internet nodes over a satellite network with inter-satellite links (ISLs). Gateways (GWs) together with Points of Presence (PoPs) support the transition between the satellite network and the Internet. UTs and GWs connect to the satellite network via serving satellites (SrvSats). As the satellites orbit the Earth at high speed, UTs and GWs frequently change their SrvSats. This causes frequent changes to their reachability, which poses a major challenge for integration. In the proposed solution, GWs and SrvSats encapsulate traffic with forwarding information so that the traffic can be carried over the satellite network towards appropriate SrvSats of UTs or GWs. The forwarding information on the encapsulating nodes is continuously updated by a controller to reflect changed SrvSats and possibly changed topology of the satellite network. Design goals for the proposed architecture were low complexity on satellites, high ability for traffic engineering, and keeping UTs out of the routing system for security and compatibility reasons. UTs may have increased security requirements (ISRs) such that their traffic should be carried within the constellation to avoid non-trusted terrestrial infrastructure. Extensions are proposed to support such ISRs. UTs may obtain either dynamic IP addresses from a nearby GW/PoP wherever they roam or they may obtain static IP addresses from a fixed Home GW/PoP. In the latter case, triangle routing via the Home GW occurs when the UT roams away from the Home GW. As this adds latency to the communication, we investigate architectural extensions for latency reduction. In addition, we show how traffic engineering can be performed in such an architecture with the help of alternate GWs and SrvSats.

## CVE-2026-120753 - Eclipse Ditto gateway accepts \`x-ditto-pre-authenticated\` from a URL query parameter, allowing unauthenticated subject impersonation (default Helm chart)

DevFeed: [CVE-2026-120753 - Eclipse Ditto gateway accepts \`x-ditto-pre-authenticated\` from a URL query parameter, allowing unauthenticated subject impersonation (default Helm chart)](<https://devfeed.tech/articles/cve-2026-120753-eclipse-ditto-gateway-accepts-x-ditto-pre-authenticated-from-a-url-query-parameter-allowing-unauthenticated-subject-impersonation-default-helm-chart-143721.md>)

Original publisher: [Read original article](<https://cvefeed.io/vuln/detail/CVE-2026-120753>)

Author: CVEFEED.io; eclipse.org

Published: 2026-11-19T14:48:18Z

Content type: news

Language: en

Sources: [Latest High/Critical Vulnerabilitiy Feed](<https://devfeed.tech/sources/latest-high-critical-vulnerabilitiy-feed.md>)

Topics: [Access Control](<https://devfeed.tech/topics/access-control.md>), [Authorization](<https://devfeed.tech/topics/authorization.md>), [nginx](<https://devfeed.tech/topics/nginx.md>), [JSON Web Tokens](<https://devfeed.tech/topics/jwt.md>), [gateway](<https://devfeed.tech/topics/gateway.md>), [Query (disambiguation)](<https://devfeed.tech/topics/query.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [cve](<https://devfeed.tech/tags/cve.md>), [cve-2026-120753](<https://devfeed.tech/tags/cve-2026-120753.md>), [ditto](<https://devfeed.tech/tags/ditto.md>), [eclipse](<https://devfeed.tech/tags/eclipse.md>), [gateway](<https://devfeed.tech/tags/gateway.md>), [helm](<https://devfeed.tech/tags/helm.md>), [helm-chart](<https://devfeed.tech/tags/helm-chart.md>), [impersonation](<https://devfeed.tech/tags/impersonation.md>), [jwt](<https://devfeed.tech/tags/jwt.md>), [nginx](<https://devfeed.tech/tags/nginx.md>), [parameter](<https://devfeed.tech/tags/parameter.md>), [policies](<https://devfeed.tech/tags/policies.md>), [policy](<https://devfeed.tech/tags/policy.md>), [proxy](<https://devfeed.tech/tags/proxy.md>), [query](<https://devfeed.tech/tags/query.md>), [remote](<https://devfeed.tech/tags/remote.md>), [things](<https://devfeed.tech/tags/things.md>), [url](<https://devfeed.tech/tags/url.md>)

### AI overview

Eclipse Ditto 1.1.0-3.9.8 can allow unauthenticated impersonation when pre-authentication is enabled: the gateway accepts a client-controlled `x-ditto-pre-authenticated` URL query parameter in addition to the trusted proxy header. In the default Helm chart configuration (`global.jwtOnly: false`), nginx skips Basic authentication for requests with a Bearer authorization header; an attacker can pair an invalid token with the query parameter, and pre-authentication occurs before JWT validation. The attacker may then read or modify Things and Policies permitted to the chosen subject. Disable gateway pre-authentication with `ENABLE_PRE_AUTHENTICATION=false`, or set Helm `global.jwtOnly: true`. The excerpt does not provide patch or fixed-version details.

### Source excerpt

CVE ID :CVE-2026-120753 Published : Nov. 19, 2026, 2:48 p.m. | 34 minutes ago Description :In Eclipse Ditto versions 1.1.0 to 3.9.8, when pre-authentication is enabled, the gateway service accepts the pre-authenticated subject not only from the `x-ditto-pre-authenticated` HTTP header set by a trusted reverse proxy, but also from an undocumented `x-ditto-pre-authenticated` URL query parameter that a client can set. A reverse proxy that only overwrites the header therefore does not stop clients from supplying their own subject. With the default configuration of the Ditto Helm chart (`global.jwtOnly: false`, which implicitly enables pre-authentication), the bundled nginx skips HTTP Basic authentication for any request with an `Authorization: Bearer` header and forwards it without the pre-authentication header. An unauthenticated remote attacker can send an invalid Bearer token together with the query parameter to authenticate as any chosen policy subject. Pre-authentication succeeds before the JWT is validated, so the attacker can read and modify Things and Policies with that subject's permissions. As a mitigation, disable pre-authentication in the gateway (`ENABLE_PRE_AUTHENTICATION=false`) or, when using the Helm chart, configure `global.jwtOnly: true`. Severity: 9.1 | CRITICAL Visit the link for more details, such as CVSS details, affected products, timeline, and more...

## A Deployment-Oriented and Resource-Efficient Neuro-Symbolic Framework for Explainable DDoS Detection in Operational Technology Networks

DevFeed: [A Deployment-Oriented and Resource-Efficient Neuro-Symbolic Framework for Explainable DDoS Detection in Operational Technology Networks](<https://devfeed.tech/articles/a-deployment-oriented-and-resource-efficient-neuro-symbolic-framework-for-explainable-ddos-detection-in-operational-technology-networks-141449.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2608.16769>)

Author: Mikiyas Alemayehu, Mohamed Chahine Ghanem, Kevin Curran, Hamza Kheddar, Ioanna Dionysiou, Elhadj Benkhelifa, J. J. Garcia-Luna-Aceves

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [DDoS](<https://devfeed.tech/topics/ddos.md>), [Security](<https://devfeed.tech/topics/security.md>), [quantization](<https://devfeed.tech/topics/quantization.md>), [gateway](<https://devfeed.tech/topics/gateway.md>)

Tags: [attack](<https://devfeed.tech/tags/attack.md>), [availability](<https://devfeed.tech/tags/availability.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [budget](<https://devfeed.tech/tags/budget.md>), [capture](<https://devfeed.tech/tags/capture.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [ddos](<https://devfeed.tech/tags/ddos.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [distributed-denial-of-service](<https://devfeed.tech/tags/distributed-denial-of-service.md>), [edge](<https://devfeed.tech/tags/edge.md>), [false-negative](<https://devfeed.tech/tags/false-negative.md>), [false-positive](<https://devfeed.tech/tags/false-positive.md>), [gateway](<https://devfeed.tech/tags/gateway.md>), [hybrid](<https://devfeed.tech/tags/hybrid.md>), [inference](<https://devfeed.tech/tags/inference.md>), [int8](<https://devfeed.tech/tags/int8.md>), [load](<https://devfeed.tech/tags/load.md>), [memory](<https://devfeed.tech/tags/memory.md>), [networks](<https://devfeed.tech/tags/networks.md>), [operational-technology](<https://devfeed.tech/tags/operational-technology.md>), [resource](<https://devfeed.tech/tags/resource.md>)

### AI overview

The proposed OT DDoS detector combines a compact GRU with a shallow, readable decision tree, selecting their score-level fusion weight and alert threshold under a validation false-positive budget. Across ten seeds on CIC-DDoS2019 at a 1% budget, its false-negative rate was 0.08%, versus 0.26% for the GRU and 0.17% for the tree. The evaluation also used capture-held-out or contiguous partitions and operational-prevalence metrics; with a day of mostly unseen attack families held out, the tree alone made the decision. On a Siemens SIMATIC IoT2050 gateway, the INT8 model took 2.9 ms per window, used 31 MB, and consumed 3.5 mJ per inference in Modbus/TCP and MQTT flood tests. The authors qualify the results: Edge-IIoTset is saturated by duplicates, the benchmarks as used lack interleaved traffic in capture order, and an unconstrained tree is more accurate on two benchmarks. The abstract therefore frames the hybrid's case around short, stable rules and measured footprint.

### Source excerpt

arXiv:2608.16769v2 Announce Type: replace Abstract: This paper presents a hybrid neural-symbolic detector of distributed denial-of-service (DDoS) attacks on the availability of operational technology (OT) networks, designed for their resource-constrained gateways, and an evaluation matched to deployment. A compact gated recurrent unit (GRU) is fused at score level with a shallow, readable decision tree, and weight and threshold are selected on validation data under an explicit false-positive budget, whose attainment in finite samples is analysed. The evaluation on CIC-DDoS2019, Edge-IIoTset and CICIoT23 uses contiguous or capture-held-out partitions, dependence-aware intervals, and precision and alert load at operational prevalence. Over ten seeds at a 1% budget, the hybrid's false-negative rate on CIC-DDoS2019 is 0.08%, against 0.26% for the GRU and 0.17% for the tree. With a day of mostly unseen attack families held out, the tree alone carries the decision. Audits bound these claims: Edge-IIoTset is saturated by duplicates, no benchmark as used provides interleaved traffic in capture order, and an unconstrained tree is more accurate on two of them, so the case for the hybrid rests on short, stable rules and a measured footprint. On a Siemens SIMATIC IoT2050 gateway, tested with Modbus/TCP and MQTT floods, the INT8 model needs 2.9 ms per window, 31 MB of memory and 3.5 mJ per inference.

## Scaling Azure Application Gateway for traffic spikes

DevFeed: [Scaling Azure Application Gateway for traffic spikes](<https://devfeed.tech/articles/scaling-azure-application-gateway-for-traffic-spikes-144741.md>)

Original publisher: [Read original article](<https://www.gremlin.com/blog/scaling-azure-application-gateway-for-traffic-spikes>)

Author: Andre Newman

Published: 2026-11-18T00:00:00Z

Content type: article

Language: en

Sources: [Gremlin Blog](<https://devfeed.tech/sources/gremlin-blog.md>)

Topics: [Azure](<https://devfeed.tech/topics/azure.md>), [Load Balancing](<https://devfeed.tech/topics/load-balancing.md>), [gateway](<https://devfeed.tech/topics/gateway.md>)

Tags: [autoscaling](<https://devfeed.tech/tags/autoscaling.md>), [azure](<https://devfeed.tech/tags/azure.md>), [black-friday](<https://devfeed.tech/tags/black-friday.md>), [capacity](<https://devfeed.tech/tags/capacity.md>), [gateway](<https://devfeed.tech/tags/gateway.md>), [scaling](<https://devfeed.tech/tags/scaling.md>), [spikes](<https://devfeed.tech/tags/spikes.md>), [use-cases](<https://devfeed.tech/tags/use-cases.md>)

### AI overview

Azure Application Gateway v2 can use manual scaling (a fixed 1-125 instances) or autoscaling (a minimum of 0-100 and an optional maximum up to 125, default 10). Fixed capacity can constrain traffic during unexpected surges and leave unused capacity running when traffic falls. Azure scales using capacity units based on the highest of compute, persistent connections, or throughput; each instance handles up to 10 units. Because new instances take three to five minutes to provision, the article suggests starting with a minimum of at least two and sizing from recent peak usage. It recommends a maximum of 125 for high-traffic gateways, a /24 subnet for v2, and alerts at 75% of recent peak capacity; workloads needing more than 125 instances can route across gateways with Traffic Manager or Front Door. Autoscaling can be enabled without redeploying through the portal, CLI, Bicep, or Terraform. Azure Resource Graph can find fixed-capacity gateways across accessible subscriptions; Gremlin also flags gateways lacking autoscaling and monitors for configuration regressions.

### Source excerpt

Fixed-capacity Azure Application Gateways limit your total traffic capacity. Learn how autoscaling works, how to enable it, and how to find gateways without it.

## Deploying an AI gateway in front of or behind your existing API gateway

DevFeed: [Deploying an AI gateway in front of or behind your existing API gateway](<https://devfeed.tech/articles/deploying-an-ai-gateway-in-front-of-or-behind-your-existing-api-gateway-134655.md>)

Original publisher: [Read original article](<https://nirmata.com/2026/11/16/deploying-an-ai-gateway-in-front-of-or-behind-your-existing-api-gateway/>)

Author: Ritesh Patel

Published: 2026-11-16T05:03:28.562711Z

Content type: tutorial

Language: en

Sources: [Nirmata](<https://devfeed.tech/sources/nirmata.md>)

Topics: [gateway](<https://devfeed.tech/topics/gateway.md>), [API Governance](<https://devfeed.tech/topics/api-governance.md>), [API Logging](<https://devfeed.tech/topics/api-logging.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [2026](<https://devfeed.tech/tags/2026.md>), [3](<https://devfeed.tech/tags/3.md>), [403](<https://devfeed.tech/tags/403.md>), [admission](<https://devfeed.tech/tags/admission.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-identity](<https://devfeed.tech/tags/agent-identity.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-gateway](<https://devfeed.tech/tags/ai-gateway.md>), [ai-governance](<https://devfeed.tech/tags/ai-governance.md>), [api](<https://devfeed.tech/tags/api.md>), [api-gateway](<https://devfeed.tech/tags/api-gateway.md>), [block](<https://devfeed.tech/tags/block.md>), [egress](<https://devfeed.tech/tags/egress.md>), [either](<https://devfeed.tech/tags/either.md>), [existing](<https://devfeed.tech/tags/existing.md>), [first](<https://devfeed.tech/tags/first.md>), [gateway](<https://devfeed.tech/tags/gateway.md>), [kubernetes](<https://devfeed.tech/tags/kubernetes.md>), [kubernetes-security](<https://devfeed.tech/tags/kubernetes-security.md>), [networking](<https://devfeed.tech/tags/networking.md>), [point](<https://devfeed.tech/tags/point.md>)

### AI overview

Choose placement by deciding which hop must inspect prompts and tool arguments first: an AI gateway in front applies its checks before API gateway policies, while one behind preserves the API gateway as the entry point and adds model rules afterward. In either design, carry verifiable per-agent identity across hops and block direct agent egress to providers; otherwise agents can bypass the gateway. Kubernetes egress NetworkPolicy works only when enforced by the cluster's network plugin, and default-deny egress also needs a DNS allowance. The excerpt recommends Gateway API for new routing and calls out cross-namespace allowedRoutes, explicit body forwarding for Envoy external processing, and monitoring fail-open counters. The example configuration is not tested on a running cluster.

### Source excerpt

An AI gateway in front of your API gateway checks agent calls first. Behind it, the API gateway stays the single entry point. Either way, block direct egress.

## Someone Built a Raspberry Pi 5 Router, and It Looks Absolutely Ridiculous

DevFeed: [Someone Built a Raspberry Pi 5 Router, and It Looks Absolutely Ridiculous](<https://devfeed.tech/articles/someone-built-a-raspberry-pi-5-router-and-it-looks-absolutely-ridiculous-134193.md>)

Original publisher: [Read original article](<https://noted.lol/raspberry-pi-5-router-pi-dock-wifi/>)

Author: Jeremy

Published: 2026-11-14T21:39:41Z

Content type: news

Language: en

Sources: [Noted](<https://devfeed.tech/sources/noted.md>)

Topics: [Raspberry Pi](<https://devfeed.tech/topics/raspberry-pi.md>), [gateway](<https://devfeed.tech/topics/gateway.md>), [Pi-hole](<https://devfeed.tech/topics/pihole.md>), [Docker Compose](<https://devfeed.tech/topics/docker-compose.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [3d-printed](<https://devfeed.tech/tags/3d-printed.md>), [access-points](<https://devfeed.tech/tags/access-points.md>), [appearance](<https://devfeed.tech/tags/appearance.md>), [community](<https://devfeed.tech/tags/community.md>), [dashboard](<https://devfeed.tech/tags/dashboard.md>), [dhcp](<https://devfeed.tech/tags/dhcp.md>), [dns](<https://devfeed.tech/tags/dns.md>), [docker](<https://devfeed.tech/tags/docker.md>), [docker-compose](<https://devfeed.tech/tags/docker-compose.md>), [documentation](<https://devfeed.tech/tags/documentation.md>), [drivers](<https://devfeed.tech/tags/drivers.md>), [ethernet](<https://devfeed.tech/tags/ethernet.md>), [github](<https://devfeed.tech/tags/github.md>), [gpl](<https://devfeed.tech/tags/gpl.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [pi-hole](<https://devfeed.tech/tags/pi-hole.md>), [raspberry-pi](<https://devfeed.tech/tags/raspberry-pi.md>), [raspberry-pi-5](<https://devfeed.tech/tags/raspberry-pi-5.md>), [router](<https://devfeed.tech/tags/router.md>), [wi-fi](<https://devfeed.tech/tags/wi-fi.md>)

### AI overview

Pi-Dock-Wifi is a Raspberry Pi 5 router that handles Wi-Fi for its creator's apartment using two MediaTek MT7915E cards for separate 2.4GHz and 5GHz access points; a PCIe switch lets both share the Pi's single PCIe connection. Docker Compose runs wireless networking, DHCP/DNS, routing, firewall rules and a dashboard, alongside Pi-hole for DNS filtering and ttyd for dashboard-accessible SSH. Health checks, network statistics, logging and Ethernet recovery are intended to reduce manual recovery, while configuration files remain directly editable. The setup requires compatible Wi-Fi hardware and drivers, a privileged host-networked Docker container, and an upstream modem or firewall. The published configuration works for the creator, but installation instructions have not been independently validated on a fresh system.

### Source excerpt

A community member built a homemade router using a Raspberry Pi 5, two Wi-Fi cards, and a tower of expansion boards. The open-source Pi-Dock-Wifi project includes Pi-hole, Docker Compose, and its own web dashboard.

## How Much Latency Does a Self-Hosted LLM Gateway Add? Langfuse vs LiteLLM vs AcruxCore

DevFeed: [How Much Latency Does a Self-Hosted LLM Gateway Add? Langfuse vs LiteLLM vs AcruxCore](<https://devfeed.tech/articles/how-much-latency-does-a-self-hosted-llm-gateway-add-langfuse-vs-litellm-vs-acruxcore-134431.md>)

Original publisher: [Read original article](<https://www.sitepoint.com/how-much-latency-does-a-self-hosted-llm-gateway-add-langfuse-vs-litellm-vs-acruxcore/>)

Author: Talha Anwar

Published: 2026-11-13T15:40:26Z

Content type: news

Language: en

Sources: [SitePoint](<https://devfeed.tech/sources/sitepoint.md>)

Topics: [litellm](<https://devfeed.tech/topics/litellm.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [gateway](<https://devfeed.tech/topics/gateway.md>), [LLM observability](<https://devfeed.tech/topics/llm-observability.md>), [Self-hosted](<https://devfeed.tech/topics/self-hosted.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-gateway](<https://devfeed.tech/tags/ai-gateway.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [budget](<https://devfeed.tech/tags/budget.md>), [clickhouse](<https://devfeed.tech/tags/clickhouse.md>), [concurrent](<https://devfeed.tech/tags/concurrent.md>), [gateway](<https://devfeed.tech/tags/gateway.md>), [langfuse](<https://devfeed.tech/tags/langfuse.md>), [latency](<https://devfeed.tech/tags/latency.md>), [litellm](<https://devfeed.tech/tags/litellm.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-gateway](<https://devfeed.tech/tags/llm-gateway.md>), [performance-scaling](<https://devfeed.tech/tags/performance-scaling.md>), [self-hosted](<https://devfeed.tech/tags/self-hosted.md>)

### AI overview

In a controlled test against the same OpenAI model, LiteLLM added 61-67 ms to non-streaming calls, AcruxCore 15-24 ms, and Langfuse's measured cost could not be distinguished from zero. For first streamed tokens, no gateway showed a consistent added delay across all runs. The result depended on controlling network effects: one OpenAI address added about 250 ms on new connections, so the test pinned the address and kept the direct client's connection open to match gateway behavior. It compared paired calls within each round and used bootstrap intervals; intervals including zero indicate uncertainty, not proof of no cost. Logging levels showed no clear effect, and overlapping intervals prevent ranking Langfuse against AcruxCore. Findings are limited to short calls, one network and latency; the test did not measure performance under load.

### Source excerpt

null Continue reading How Much Latency Does a Self-Hosted LLM Gateway Add? Langfuse vs LiteLLM vs AcruxCore on SitePoint.

## PHP2Shell Exploited in Destructive Check Point Gateway Attacks

DevFeed: [PHP2Shell Exploited in Destructive Check Point Gateway Attacks](<https://devfeed.tech/articles/php2shell-exploited-in-destructive-check-point-gateway-attacks-131328.md>)

Original publisher: [Read original article](<https://www.securityweek.com/php2shell-exploited-in-destructive-check-point-gateway-attacks/>)

Author: Ionut Arghire

Published: 2026-11-13T07:39:04Z

Content type: news

Language: en

Sources: [SecurityWeek](<https://devfeed.tech/sources/securityweek.md>)

Topics: [known exploitable vulnerabilities](<https://devfeed.tech/topics/known-exploitable-vulnerabilities.md>), [Cybersecurity](<https://devfeed.tech/topics/cybersecurity.md>), [gateway](<https://devfeed.tech/topics/gateway.md>)

Tags: [appliances](<https://devfeed.tech/tags/appliances.md>), [asset-discovery](<https://devfeed.tech/tags/asset-discovery.md>), [attacks](<https://devfeed.tech/tags/attacks.md>), [backdoor](<https://devfeed.tech/tags/backdoor.md>), [campaign](<https://devfeed.tech/tags/campaign.md>), [check-point](<https://devfeed.tech/tags/check-point.md>), [china](<https://devfeed.tech/tags/china.md>), [code-execution](<https://devfeed.tech/tags/code-execution.md>), [commands](<https://devfeed.tech/tags/commands.md>), [critical-vulnerabilities](<https://devfeed.tech/tags/critical-vulnerabilities.md>), [cve-2026-109618](<https://devfeed.tech/tags/cve-2026-109618.md>), [cve-2026-109619](<https://devfeed.tech/tags/cve-2026-109619.md>), [cve-2026-123039](<https://devfeed.tech/tags/cve-2026-123039.md>), [cybersecurity](<https://devfeed.tech/tags/cybersecurity.md>), [directory](<https://devfeed.tech/tags/directory.md>), [dream](<https://devfeed.tech/tags/dream.md>), [exploited](<https://devfeed.tech/tags/exploited.md>), [featured](<https://devfeed.tech/tags/featured.md>), [gateway](<https://devfeed.tech/tags/gateway.md>), [malware-threats](<https://devfeed.tech/tags/malware-threats.md>), [php2shell](<https://devfeed.tech/tags/php2shell.md>), [root](<https://devfeed.tech/tags/root.md>), [vulnerabilities](<https://devfeed.tech/tags/vulnerabilities.md>)

### AI overview

Attackers used PHP2Shell vulnerabilities (CVE-2026-109618 and CVE-2026-109619) for initial access to Check Point gateways, then exploited CVE-2026-123039 in DynamicCLI to gain root access. The first wave began October 30 against Israeli organizations: attackers planted PHP webshells in the Mobile Access portal directory, deployed TSGA and TSProxy for backdoor access and network interception, conducted internal discovery, moved to a VMware ESXi host, and ran a wiper. A second wave began November 2 across multiple countries; no destructive activity was observed in that wave. Check Point says the evidence does not support high-confidence attribution: Chinese working-hour activity and China-linked malware and infrastructure coexist with destructive tactics that do not fit known Chinese operations, leaving actor participation, access brokering, false flag, and smoke-screen scenarios plausible.

### Source excerpt

PHP2Shell enabled initial compromise, while CVE-2026-123039 allowed attackers to elevate privileges to root. The post PHP2Shell Exploited in Destructive Check Point Gateway Attacks appeared first on SecurityWeek.

## Citrix NetScaler: When the Enterprise Gateway Becomes the Risk

DevFeed: [Citrix NetScaler: When the Enterprise Gateway Becomes the Risk](<https://devfeed.tech/articles/citrix-netscaler-when-the-enterprise-gateway-becomes-the-risk-131266.md>)

Original publisher: [Read original article](<https://thecyberthrone.in/2026/11/13/citrix-netscaler-when-the-enterprise-gateway-becomes-the-risk/>)

Author: PravinKarthik

Published: 2026-11-13T01:23:55Z

Content type: article

Language: en

Sources: [Cyber Newsroom](<https://devfeed.tech/sources/cyber-newsroom.md>)

Topics: [Security](<https://devfeed.tech/topics/security.md>), [cve remediation](<https://devfeed.tech/topics/cve-remediation.md>), [network security](<https://devfeed.tech/topics/network-security.md>), [gateway](<https://devfeed.tech/topics/gateway.md>)

Tags: [aaa](<https://devfeed.tech/tags/aaa.md>), [adc](<https://devfeed.tech/tags/adc.md>), [application-delivery](<https://devfeed.tech/tags/application-delivery.md>), [asset-discovery](<https://devfeed.tech/tags/asset-discovery.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [balancing](<https://devfeed.tech/tags/balancing.md>), [cert-eu](<https://devfeed.tech/tags/cert-eu.md>), [citrix](<https://devfeed.tech/tags/citrix.md>), [citrix-netscaler](<https://devfeed.tech/tags/citrix-netscaler.md>), [component](<https://devfeed.tech/tags/component.md>), [critical-vulnerabilities](<https://devfeed.tech/tags/critical-vulnerabilities.md>), [cve](<https://devfeed.tech/tags/cve.md>), [cve-2026-107412](<https://devfeed.tech/tags/cve-2026-107412.md>), [cve-2026-120868](<https://devfeed.tech/tags/cve-2026-120868.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [gateway](<https://devfeed.tech/tags/gateway.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [netscaler](<https://devfeed.tech/tags/netscaler.md>), [november-2026](<https://devfeed.tech/tags/november-2026.md>), [risk](<https://devfeed.tech/tags/risk.md>), [security](<https://devfeed.tech/tags/security.md>), [vulnerabilities](<https://devfeed.tech/tags/vulnerabilities.md>)

### AI overview

Citrix disclosed 28 vulnerabilities in NetScaler ADC and Gateway on November 12, 2026, including critical memory corruption and overflow flaws. CVE-2026-120868 (CVSS 9.3) affects all deployments, including default configurations; CVE-2026-107412 (CVSS 9.5) affects appliances configured as Gateway or AAA virtual servers. Other flaws depend on features or services such as DNS, SMPP, authentication, Application Firewall, HTTP/2, or HTTP/3. As of November 13, the excerpt reports no confirmed exploitation or public proof of concept in the referenced CERT-EU assessment. Citrix fixed releases are 14.1-73.57, 13.1-64.39, 14.1-73.58 FIPS, and 13.1-37.293 FIPS/NDcPP, or later; those deployments should follow their respective release requirements. The recommended response is to inventory appliances, assess feature exposure, prioritize internet-facing Gateway and AAA systems, upgrade, then validate authentication, VPN, application delivery, and critical services.

### Source excerpt

Citrix NetScaler: When the Enterprise Gateway Becomes the Risk The StoryEnterprise security often focuses on protecting endpoints, applications and cloud workloads. But what happens when the infrastructure connecting all of them becomes the problem?Citrix NetScal ... Read more Published Date: Nov 13, 2026 (5 hours, 8 minutes ago) Vulnerabilities has been mentioned in this article. CVE-2026-107412 CVE-2026-120868 CVE-2026-119618

## Mikrotik KNOT Gateway HL9 - An outdoor Wi-Fi HaLow IoT gateway with GbE, WiFi 6, BLE 5.1, 4G LTE Cat 1 bis, and GNSS

DevFeed: [Mikrotik KNOT Gateway HL9 - An outdoor Wi-Fi HaLow IoT gateway with GbE, WiFi 6, BLE 5.1, 4G LTE Cat 1 bis, and GNSS](<https://devfeed.tech/articles/mikrotik-knot-gateway-hl9-an-outdoor-wi-fi-halow-iot-gateway-with-gbe-wifi-6-ble-5-1-4g-lte-cat-1-bis-and-gnss-128995.md>)

Original publisher: [Read original article](<https://www.cnx-software.com/2026/11/11/mikrotik-knot-gateway-hl9-an-outdoor-wi-fi-halow-iot-gateway-with-gbe-wifi-6-ble-5-1-4g-lte-cat-1-bis-and-gnss/>)

Author: Debashis Das

Published: 2026-11-11T10:22:21Z

Content type: release

Language: en

Sources: [CNX Software - Embedded Systems News](<https://devfeed.tech/sources/cnx-software-embedded-systems-news.md>)

Topics: [gateway](<https://devfeed.tech/topics/gateway.md>), [Internet of things](<https://devfeed.tech/topics/iot.md>), [4g lte](<https://devfeed.tech/topics/4g-lte.md>), [Bluetooth](<https://devfeed.tech/topics/bluetooth.md>), [MikroTik](<https://devfeed.tech/topics/mikrotik.md>)

Tags: [4g-lte](<https://devfeed.tech/tags/4g-lte.md>), [802-11ah](<https://devfeed.tech/tags/802-11ah.md>), [applications](<https://devfeed.tech/tags/applications.md>), [arm](<https://devfeed.tech/tags/arm.md>), [arm64](<https://devfeed.tech/tags/arm64.md>), [asset](<https://devfeed.tech/tags/asset.md>), [backhaul](<https://devfeed.tech/tags/backhaul.md>), [ble](<https://devfeed.tech/tags/ble.md>), [bluetooth](<https://devfeed.tech/tags/bluetooth.md>), [cellular](<https://devfeed.tech/tags/cellular.md>), [gateway](<https://devfeed.tech/tags/gateway.md>), [gnss](<https://devfeed.tech/tags/gnss.md>), [halow](<https://devfeed.tech/tags/halow.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [industrial](<https://devfeed.tech/tags/industrial.md>), [iot](<https://devfeed.tech/tags/iot.md>), [linux](<https://devfeed.tech/tags/linux.md>), [lte](<https://devfeed.tech/tags/lte.md>), [mikrotik](<https://devfeed.tech/tags/mikrotik.md>), [outdoor](<https://devfeed.tech/tags/outdoor.md>), [poe](<https://devfeed.tech/tags/poe.md>), [qualcomm-atheros](<https://devfeed.tech/tags/qualcomm-atheros.md>), [wi-fi](<https://devfeed.tech/tags/wi-fi.md>), [wi-fi-halow](<https://devfeed.tech/tags/wi-fi-halow.md>), [wifi-6](<https://devfeed.tech/tags/wifi-6.md>)

### AI overview

The MikroTik KNOT Gateway HL9 combines 915 MHz Wi-Fi HaLow, Bluetooth 5.1, 2.4 GHz Wi-Fi 6, LTE Cat 1 bis, Gigabit Ethernet, and GNSS in an IP66 outdoor enclosure. Its dual-core Qualcomm IPQ-5010 processor, 256 MB RAM, and RouterOS v7 support local processing and filtering of Bluetooth advertisements, with sensor data forwarded by MQTT or HTTP; RouterOS scripts enable custom monitoring and automation. Power is available through 802.3af/at PoE or a separate DC input. The gateway supports eSIM-based cellular service through MikroTik Connectivity as well as a nano-SIM slot. The related KNOT Gateway LR8 shares several core specifications but uses 868 MHz LoRa instead of Wi-Fi HaLow and has different LTE bands. MikroTik recommends RouterOS v7.23.1 or the latest stable release for regulatory compliance and promises updates for the product's lifetime or at least five years from purchase.

### Source excerpt

MikroTik KNOT Gateway HL9 is an IP66-rated outdoor IoT gateway that combines 915 MHz Wi-Fi HaLow (802.11ah), Bluetooth 5.1, Wi-Fi 6, LTE Cat 1 bis, Gigabit Ethernet, and GNSS. The gateway supports asset tracking, remote sensor monitoring, industrial IoT, and agricultural applications. Built around a dual-core Qualcomm IPQ-5010 ARM64 processor, it features 256MB RAM and 128MB NAND flash. It relies on a Morse Micro MM6108 Wi-Fi HaLow SoC for sub-GHz connectivity, with Gigabit Ethernet, 2.4 GHz Wi-Fi 6, and LTE Cat 1 bis cellular for backhaul. MikroTik KNOT Gateway HL9 specifications: SoC - Qualcomm IPQ-5010 dual-core 64-bit Arm processor @ 800 MHz Memory - 256MB RAM Storage - 128MB NAND flash Connectivity Ethernet - Gigabit Ethernet RJ45 port with 802.3af/at PoE-in support Wi-Fi HaLow - 915 MHz IEEE 802.11ah via Morse Micro MM6108 SoC Wi-Fi - 2.4 GHz Wi-Fi 6 (802.11b/g/n/ax), 1x1, up to 287 Mbps, 3.9 dBi integrated antenna [...] The post Mikrotik KNOT Gateway HL9 - An outdoor Wi-Fi HaLow IoT gateway with GbE, WiFi 6, BLE 5.1, 4G LTE Cat 1 bis, and GNSS appeared first on CNX Software - Embedded Systems News.

## EVPN-VXLAN with Distributed Anycast Gateway on VyOS

DevFeed: [EVPN-VXLAN with Distributed Anycast Gateway on VyOS](<https://devfeed.tech/articles/evpn-vxlan-with-distributed-anycast-gateway-on-vyos-129263.md>)

Original publisher: [Read original article](<https://blog.vyos.io/evpn-vxlan-distributed-anycast-gateway-vyos>)

Author: f.maidana@vyos.io (Fernando Maidana)

Published: 2026-11-11T10:09:01Z

Content type: article

Language: en

Sources: [VyOS](<https://devfeed.tech/sources/vyos-blog.md>)

Topics: [gateway](<https://devfeed.tech/topics/gateway.md>), [evpn](<https://devfeed.tech/topics/evpn.md>), [VXLAN](<https://devfeed.tech/topics/vxlan.md>), [control-plane](<https://devfeed.tech/topics/control-plane.md>)

Tags: [anycast-gateway](<https://devfeed.tech/tags/anycast-gateway.md>), [arp](<https://devfeed.tech/tags/arp.md>), [bfd](<https://devfeed.tech/tags/bfd.md>), [bgp](<https://devfeed.tech/tags/bgp.md>), [bgp-evpn](<https://devfeed.tech/tags/bgp-evpn.md>), [border-router](<https://devfeed.tech/tags/border-router.md>), [boundary](<https://devfeed.tech/tags/boundary.md>), [bridge](<https://devfeed.tech/tags/bridge.md>), [control-plane](<https://devfeed.tech/tags/control-plane.md>), [data-center](<https://devfeed.tech/tags/data-center.md>), [distributed-routing](<https://devfeed.tech/tags/distributed-routing.md>), [ebgp](<https://devfeed.tech/tags/ebgp.md>), [edge-routing](<https://devfeed.tech/tags/edge-routing.md>), [evpn](<https://devfeed.tech/tags/evpn.md>), [fabric](<https://devfeed.tech/tags/fabric.md>), [failover](<https://devfeed.tech/tags/failover.md>), [firewall](<https://devfeed.tech/tags/firewall.md>), [flow](<https://devfeed.tech/tags/flow.md>), [high-availability](<https://devfeed.tech/tags/high-availability.md>), [ibgp](<https://devfeed.tech/tags/ibgp.md>), [identity](<https://devfeed.tech/tags/identity.md>), [interface](<https://devfeed.tech/tags/interface.md>), [ip](<https://devfeed.tech/tags/ip.md>), [location](<https://devfeed.tech/tags/location.md>), [mobility](<https://devfeed.tech/tags/mobility.md>), [multihoming](<https://devfeed.tech/tags/multihoming.md>), [route-maps](<https://devfeed.tech/tags/route-maps.md>), [routing-policy](<https://devfeed.tech/tags/routing-policy.md>), [traffic](<https://devfeed.tech/tags/traffic.md>), [vrrp](<https://devfeed.tech/tags/vrrp.md>), [vxlan](<https://devfeed.tech/tags/vxlan.md>), [vyos](<https://devfeed.tech/tags/vyos.md>)

### AI overview

VyOS places the same gateway IP and MAC on a pseudo-Ethernet interface on each participating leaf/VTEP, avoiding Duplicate Address Detection issues from configuring the shared address directly on multiple interfaces. VLANs map to VXLAN VNIs, while BGP EVPN distributes endpoint reachability. For inter-subnet traffic, the local leaf routes the packet and uses EVPN-VXLAN to reach the destination, avoiding a centralized gateway path. When a workload moves between leaves within its VLAN, it retains its IP and gateway settings; EVPN updates its attachment location. The text summarizes the architecture and behavior but points to a separate deployment guide for complete configuration and validation steps.

### Source excerpt

Modern data center fabrics commonly combine BGP EVPN as the control plane with VXLAN as the data plane. In this architecture, a distributed anycast gateway places Layer 3 gateway functionality directly on multiple leaf switches (VTEPs), bringing routing closer to connected workloads. This post summarizes how VyOS implements the anycast gateway, how traffic moves through the fabric, and why the model matters for workload mobility. For the complete configuration and validation steps, see the EVPN-VXLAN Anycast Gateway Deployment Guide.

## SAP Patches Four CVSS 10.0 Flaws, Including Two Enabling Remote Code Execution

DevFeed: [SAP Patches Four CVSS 10.0 Flaws, Including Two Enabling Remote Code Execution](<https://devfeed.tech/articles/sap-patches-four-cvss-10-0-flaws-including-two-enabling-remote-code-execution-126342.md>)

Original publisher: [Read original article](<https://thehackernews.com/2026/11/sap-patches-four-cvss-100-flaws.html>)

Author: The Hacker News

Published: 2026-11-10T10:02:40Z

Content type: news

Language: en

Sources: [Cyber Newsroom](<https://devfeed.tech/sources/cyber-newsroom.md>)

Topics: [code security](<https://devfeed.tech/topics/code-security.md>), [patches](<https://devfeed.tech/topics/patches.md>), [Security research](<https://devfeed.tech/topics/security-research.md>), [gateway](<https://devfeed.tech/topics/gateway.md>)

Tags: [authentication](<https://devfeed.tech/tags/authentication.md>), [code-execution](<https://devfeed.tech/tags/code-execution.md>), [cve-2026-120017](<https://devfeed.tech/tags/cve-2026-120017.md>), [cve-2026-89103](<https://devfeed.tech/tags/cve-2026-89103.md>), [cve-2026-89126](<https://devfeed.tech/tags/cve-2026-89126.md>), [cvss](<https://devfeed.tech/tags/cvss.md>), [enterprise-security](<https://devfeed.tech/tags/enterprise-security.md>), [patches](<https://devfeed.tech/tags/patches.md>), [remote-code-execution](<https://devfeed.tech/tags/remote-code-execution.md>), [sap](<https://devfeed.tech/tags/sap.md>), [security](<https://devfeed.tech/tags/security.md>), [vulnerabilities](<https://devfeed.tech/tags/vulnerabilities.md>), [vulnerability](<https://devfeed.tech/tags/vulnerability.md>), [web-security](<https://devfeed.tech/tags/web-security.md>)

### AI overview

SAP's November 2026 bulletin fixes four unauthenticated, no-user-action flaws rated CVSS 10.0: SAML 2.0 could permit login as any user, including privileged users on some systems; SAP Gateway could treat an outsider as an internal application server and allow unauthorized actions; and flaws in the Internet Communication Manager (ICM) and Web Dispatcher could corrupt memory and enable code execution. The ICM and Web Dispatcher flaws share a WebSocket parsing bug; WebSocket support is enabled by default. SAP and researchers recommend prioritizing the component-specific fixes. Check SAML logons and trusted identity providers; for Gateway, review and restrict prxyinfo or set gw/acl_mode_proxy to 1 where applicable, since patching alone may not close exposure. Patch every Web Dispatcher and ICM. Temporary Web Dispatcher shielding of ICM works only when the ICM cannot be reached directly and the dispatcher is not configured as a router. Disabling WebSockets can block the ICM and Web Dispatcher bugs but may break dependent features. Out-of-maintenance kernels may need an upgrade, and kernel patch levels vary in whether they contain the fix. Researchers reported no observed exploitation.

### Source excerpt

SAP Patches Four CVSS 10.0 Flaws, Including Two Enabling Remote Code Execution Four flaws that attackers could exploit without logging in were fixed today as part of SAP's monthly Security Patch Day--the vendor rates all four 10.0, the maximum CVSS score. Three are in the SAP Net ... Read more Published Date: Nov 10, 2026 (3 hours, 24 minutes ago) Vulnerabilities has been mentioned in this article. CVE-2026-89126 CVE-2026-89103 CVE-2026-76964 CVE-2026-120017 CVE-2026-44748

## AI Token Economics & Cost Control with Nutanix Agent Gateway

DevFeed: [AI Token Economics & Cost Control with Nutanix Agent Gateway](<https://devfeed.tech/articles/ai-token-economics-cost-control-with-nutanix-agent-gateway-126836.md>)

Original publisher: [Read original article](<https://www.nutanix.com/blog/taming-token-sprawl-nutanix-agent-gateway-for-regulated-industries>)

Author: Leah Gabbert

Published: 2026-11-10T07:53:12Z

Content type: article

Language: en

Sources: [Nutanix](<https://devfeed.tech/sources/nutanix.md>)

Topics: [nutanix](<https://devfeed.tech/topics/nutanix.md>), [control-plane](<https://devfeed.tech/topics/control-plane.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [gateway](<https://devfeed.tech/topics/gateway.md>), [Access Control](<https://devfeed.tech/topics/access-control.md>), [Sovereign AI](<https://devfeed.tech/topics/sovereign-ai.md>), [Self Hosted AI Tools](<https://devfeed.tech/topics/self-hosted-ai-tools.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-gateway](<https://devfeed.tech/tags/agent-gateway.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-costs](<https://devfeed.tech/tags/ai-costs.md>), [blog-category](<https://devfeed.tech/tags/blog-category.md>), [control](<https://devfeed.tech/tags/control.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cost-control](<https://devfeed.tech/tags/cost-control.md>), [costs](<https://devfeed.tech/tags/costs.md>), [data](<https://devfeed.tech/tags/data.md>), [economics](<https://devfeed.tech/tags/economics.md>), [education](<https://devfeed.tech/tags/education.md>), [enterprise-ai](<https://devfeed.tech/tags/enterprise-ai.md>), [financial-services](<https://devfeed.tech/tags/financial-services.md>), [gateway](<https://devfeed.tech/tags/gateway.md>), [generative](<https://devfeed.tech/tags/generative.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [government](<https://devfeed.tech/tags/government.md>), [healthcare](<https://devfeed.tech/tags/healthcare.md>), [industries](<https://devfeed.tech/tags/industries.md>), [manage](<https://devfeed.tech/tags/manage.md>), [models](<https://devfeed.tech/tags/models.md>), [nutanix](<https://devfeed.tech/tags/nutanix.md>), [nutanix-enterprise-ai-nai](<https://devfeed.tech/tags/nutanix-enterprise-ai-nai.md>), [retail-consumer](<https://devfeed.tech/tags/retail-consumer.md>), [tof-awareness](<https://devfeed.tech/tags/tof-awareness.md>), [token](<https://devfeed.tech/tags/token.md>), [token-economics](<https://devfeed.tech/tags/token-economics.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

Agentic AI costs can rise as agents make repeated model calls and accumulate context, so Nutanix Agent Gateway offers a centralized point to manage model and tool access, monitor consumption, and set administrator-configured usage limits. Its rule-based routing can send simpler queries to local or self-hosted models and more complex tasks to premium models; supported integrations can also route across public and private providers through one API. For regulated environments, the text describes role-based access controls, MCP tool filtering, and air-gapped deployments as options, subject to architecture, configuration, and support. These controls provide oversight and cost management, but the text does not claim they guarantee savings or compliance.

### Source excerpt

Learn how Nutanix Agent Gateway helps regulated industries manage AI token economics, control generative AI costs and govern agent access to models and data.

## Wirken: Open-source AI agent gateway

DevFeed: [Wirken: Open-source AI agent gateway](<https://devfeed.tech/articles/wirken-open-source-ai-agent-gateway-122826.md>)

Original publisher: [Read original article](<https://www.helpnetsecurity.com/2026/11/09/wirken-open-source-ai-agent-gateway/>)

Author: Anamarija Pogorelec

Published: 2026-11-09T06:00:12Z

Content type: article

Language: en

Sources: [Help Net Security](<https://devfeed.tech/sources/help-net-security.md>)

Topics: [gateway](<https://devfeed.tech/topics/gateway.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [Coalition for Secure AI](<https://devfeed.tech/topics/coalition-for-secure-ai.md>)

Tags: [actions](<https://devfeed.tech/tags/actions.md>), [agent-gateway](<https://devfeed.tech/tags/agent-gateway.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [client](<https://devfeed.tech/tags/client.md>), [commands](<https://devfeed.tech/tags/commands.md>), [container](<https://devfeed.tech/tags/container.md>), [credentials](<https://devfeed.tech/tags/credentials.md>), [cybersecurity](<https://devfeed.tech/tags/cybersecurity.md>), [data-security](<https://devfeed.tech/tags/data-security.md>), [detection](<https://devfeed.tech/tags/detection.md>), [discord](<https://devfeed.tech/tags/discord.md>), [don-t-miss](<https://devfeed.tech/tags/don-t-miss.md>), [email](<https://devfeed.tech/tags/email.md>), [encrypted](<https://devfeed.tech/tags/encrypted.md>), [ephemeral](<https://devfeed.tech/tags/ephemeral.md>), [files](<https://devfeed.tech/tags/files.md>), [gateway](<https://devfeed.tech/tags/gateway.md>), [github](<https://devfeed.tech/tags/github.md>), [google-chat](<https://devfeed.tech/tags/google-chat.md>), [hash](<https://devfeed.tech/tags/hash.md>), [messaging-apps](<https://devfeed.tech/tags/messaging-apps.md>), [news](<https://devfeed.tech/tags/news.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [signal](<https://devfeed.tech/tags/signal.md>), [software](<https://devfeed.tech/tags/software.md>), [telegram](<https://devfeed.tech/tags/telegram.md>), [whatsapp](<https://devfeed.tech/tags/whatsapp.md>)

### AI overview

Wirken is an open-source gateway connecting messaging channels to AI agents, designed to restrict what a compromised agent can access. Each channel runs in a separate process holding only its credentials; credentials are stored in an encrypted vault and supplied at the edge. Shell commands run in an ephemeral, network-isolated container, and are refused if the sandbox is unavailable. Reads proceed freely; changes require first-time approval, while deletion, installation, and credential access require approval each time. Actions are recorded before execution in a signed, hash-chained log, with offline verification. Limits include partly contained outbound traffic, injection detection that flags but does not block input, and shared-address-space agents. In shared channels, one person's Tier 2 approval covers all senders until it expires. Docker is required for sandboxed commands; disabling the sandbox permits uncontained execution. The excerpt also notes that deleting the data directory removes the audit log and that an attacker with the same user access who can rewrite both log and key may evade tamper checks.

### Source excerpt

Wirken is an open-source gateway that sits between messaging apps and AI agents. It assumes any agent can be turned against its owner and limits what a compromised one can reach. Take an agent that reads your chats and email, holds the keys to your accounts and can run commands. One hidden instruction in a message or a shared document could talk it into leaking a secret or rewriting files. Wirken connects Signal, WhatsApp, Telegram, ... More -> The post Wirken: Open-source AI agent gateway appeared first on Help Net Security.

## Free the Model, Sell the Gateway: Prompt Adware hidden in Jailbreak Bundles

DevFeed: [Free the Model, Sell the Gateway: Prompt Adware hidden in Jailbreak Bundles](<https://devfeed.tech/articles/free-the-model-sell-the-gateway-prompt-adware-hidden-in-jailbreak-bundles-114280.md>)

Original publisher: [Read original article](<https://research.checkpoint.com/2026/free-the-model-sell-the-gateway-prompt-adware-hidden-in-jailbreak-bundles/>)

Author: stcpresearch

Published: 2026-11-03T13:57:04Z

Content type: article

Language: en

Sources: [Check Point Research](<https://devfeed.tech/sources/check-point-research.md>)

Topics: [Prompt Engineering](<https://devfeed.tech/topics/prompt-engineering.md>), [prompt injection](<https://devfeed.tech/topics/prompt-injection.md>), [gateway](<https://devfeed.tech/topics/gateway.md>), [Tool](<https://devfeed.tech/topics/tool.md>)

Tags: [actor](<https://devfeed.tech/tags/actor.md>), [ads](<https://devfeed.tech/tags/ads.md>), [advertisement](<https://devfeed.tech/tags/advertisement.md>), [adware](<https://devfeed.tech/tags/adware.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-skills](<https://devfeed.tech/tags/agent-skills.md>), [ai](<https://devfeed.tech/tags/ai.md>), [attack](<https://devfeed.tech/tags/attack.md>), [business](<https://devfeed.tech/tags/business.md>), [check-point-research](<https://devfeed.tech/tags/check-point-research.md>), [check-point-research-publications](<https://devfeed.tech/tags/check-point-research-publications.md>), [cobalt-strike](<https://devfeed.tech/tags/cobalt-strike.md>), [framework](<https://devfeed.tech/tags/framework.md>), [gateway](<https://devfeed.tech/tags/gateway.md>), [jailbreak](<https://devfeed.tech/tags/jailbreak.md>), [prompt](<https://devfeed.tech/tags/prompt.md>), [toolkit](<https://devfeed.tech/tags/toolkit.md>), [tools](<https://devfeed.tech/tags/tools.md>), [webserver](<https://devfeed.tech/tags/webserver.md>)

### AI overview

Check Point Research analyzed Haiou 4.5.0, a Codex jailbreak bundle whose installer decrypts and extracts packaged prompts and six security-focused Skills. One prompt modifies global agent instructions so exact greeting triggers produce a catchphrase advertising the author's OpenAI-compatible LLM gateway. The researchers call this "prompt adware": persistent instruction changes that promote a commercial service through natural language rather than executable payloads. The package also includes an uninstaller that restores prior configurations. Its prompts target hacking-related tasks, and researchers observed the bundle alongside tools used by a cybercrime actor; they found no evidence linking its author to cybercrime. The gateway itself is not shown to be malicious, though the article notes that gateways can pose data and agent-session risks. The analyzed Codex version contains ad injection; the Claude repository did not, and Claude Code reportedly rejected the injection during testing.

### Source excerpt

Key Points Free the Model, Sell the Gateway: Prompt Adware hidden in Jailbreak Bundles Check Point Research found a misconfigured webserver of a threat actor operating the Cobalt Strike framework. Besides an open Cobalt Strike server, whose logs showed the actor compromising various private computers of Chinese speaking individuals, other tools from the toolkit of [...] The post Free the Model, Sell the Gateway: Prompt Adware hidden in Jailbreak Bundles appeared first on Check Point Research.

## 6 Best Enterprise AI Gateway Platforms

DevFeed: [6 Best Enterprise AI Gateway Platforms](<https://devfeed.tech/articles/6-best-enterprise-ai-gateway-platforms-114256.md>)

Original publisher: [Read original article](<https://www.lyzr.ai/blog/best-enterprise-ai-gateway-platforms/>)

Author: Lyzr Team

Published: 2026-11-03T08:20:03Z

Content type: comparison

Language: en

Sources: [Lyzr.ai](<https://devfeed.tech/sources/lyzr-ai.md>)

Topics: [gateway](<https://devfeed.tech/topics/gateway.md>), [Self Hosted AI Tools](<https://devfeed.tech/topics/self-hosted-ai-tools.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Claude](<https://devfeed.tech/topics/claude.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-control](<https://devfeed.tech/tags/agent-control.md>), [agent-discovery](<https://devfeed.tech/tags/agent-discovery.md>), [agent-gateway](<https://devfeed.tech/tags/agent-gateway.md>), [agent-guardrails](<https://devfeed.tech/tags/agent-guardrails.md>), [agent-sprawl](<https://devfeed.tech/tags/agent-sprawl.md>), [agent-tools](<https://devfeed.tech/tags/agent-tools.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agent-governance](<https://devfeed.tech/tags/ai-agent-governance.md>), [ai-agent-sprawl](<https://devfeed.tech/tags/ai-agent-sprawl.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-gateway](<https://devfeed.tech/tags/ai-gateway.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [ai-policy](<https://devfeed.tech/tags/ai-policy.md>), [best](<https://devfeed.tech/tags/best.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [enterprise-ai](<https://devfeed.tech/tags/enterprise-ai.md>), [gateway](<https://devfeed.tech/tags/gateway.md>), [platforms](<https://devfeed.tech/tags/platforms.md>)

### AI overview

An enterprise AI gateway centralizes identity, budgets, routing, guardrails and logging for model and agent traffic, but each platform lineage has blind spots. The guide compares six options: Lyzr Opencontroller emphasizes in-network or air-gapped deployment and discovery of unregistered agents; Kong extends governance for existing Kong users; Azure API Management fits Azure-centered estates; Apigee connects managed APIs to MCP tools; Prisma AIRS focuses on inline security inspection with a hybrid data plane; and TrueFoundry combines gateway functions with model hosting. Only Opencontroller and TrueFoundry are said to document fully air-gapped installs. The guide recommends a two-week bake-off: mirror representative traffic, verify hard budget blocks and traces, compare provider invoices with gateway logs to find bypassing agents, and measure P95 overhead on real payloads. It cautions that direct provider calls using agents' own keys remain invisible unless separately discovered.

### Source excerpt

TL;DR Lyzr built Opencontroller after its own AI tools bill reached about $50,000 a month, roughly $36,000 of it Anthropic, and it needed a more...

## Scaling LLM Agent Tool Access: The MCP Gateway

DevFeed: [Scaling LLM Agent Tool Access: The MCP Gateway](<https://devfeed.tech/articles/scaling-llm-agent-tool-access-the-mcp-gateway-113763.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2607.15593>)

Author: Mingxin Li, Enge Song, Yueshang Zuo, Xiaodong Liu, Rong Wen, Qiang Fu, Gianni Antichi, Jian He, Jing Tie, Zhou Shao, Xiaobo Xue, Xiong Xiao, Luyao Zhong, Shaokai Zhang, Jiangu Zhao, Jianyuan Lu, Shize

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Distributed Computing](<https://devfeed.tech/sources/arxiv-distributed-computing.md>), [arXiv: Networking](<https://devfeed.tech/sources/arxiv-networking.md>)

Topics: [gateway](<https://devfeed.tech/topics/gateway.md>), [MSP MCP](<https://devfeed.tech/topics/msp-mcp.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [context window](<https://devfeed.tech/topics/context-window.md>), [Cloud Architecture](<https://devfeed.tech/topics/cloud-architecture.md>), [OpenAPI Specification](<https://devfeed.tech/topics/openapi.md>), [Authorization](<https://devfeed.tech/topics/authorization.md>)

Tags: [access-control](<https://devfeed.tech/tags/access-control.md>), [affinity](<https://devfeed.tech/tags/affinity.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [compatibility](<https://devfeed.tech/tags/compatibility.md>), [complexity](<https://devfeed.tech/tags/complexity.md>), [context-window](<https://devfeed.tech/tags/context-window.md>), [conversion](<https://devfeed.tech/tags/conversion.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-dc](<https://devfeed.tech/tags/cs-dc.md>), [cs-ni](<https://devfeed.tech/tags/cs-ni.md>), [deployments](<https://devfeed.tech/tags/deployments.md>), [engine](<https://devfeed.tech/tags/engine.md>), [gateway](<https://devfeed.tech/tags/gateway.md>), [hybrid](<https://devfeed.tech/tags/hybrid.md>), [inference](<https://devfeed.tech/tags/inference.md>), [llm](<https://devfeed.tech/tags/llm.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [mcp-gateway](<https://devfeed.tech/tags/mcp-gateway.md>), [scaling](<https://devfeed.tech/tags/scaling.md>), [tool](<https://devfeed.tech/tags/tool.md>)

### AI overview

The MCP Gateway addresses production scaling problems on both sides of tool access: legacy services and changing MCP variants burden providers, while large mounted tool sets increase agent context use and latency and may lower task success. It centralizes legacy-service integration, protocol compatibility, access control, tool recommendation, and session-aware routing. Its conversion module supports 315 OpenAPI services, and its hybrid retrieval engine reports about 98% Top-15 recall while scaling access to 3,000+ tools with improved tool selection accuracy. The abstract does not provide further evaluation details.

### Source excerpt

arXiv:2607.15593v2 Announce Type: replace Abstract: LLM agents increasingly rely on tool calling to complete tasks. Model Context Protocol (MCP) standardizes tool calling between LLM agents and tool providers. It reduces integration cost and drives rapid growth in tool scale. In production deployments, tool access becomes difficult to scale. On the tool provider side, legacy services are not directly callable through MCP; the rapid protocol development creates ongoing compatibility cost. On the agent side, the number of mounted tools is limited by the LLM context window and inference overhead; mounting a large tool set increases token usage and inference latency and can reduce task success rate. Moreover, for stateful MCP backends with multiple replicas, preserving session affinity increases client-side complexity. We present a cloud-scale MCP Gateway system. It breaks the direct-connect model on the data plane and offloads legacy service integration, consolidating incompatible MCP variants, access control, tool recommendation, and session-aware routing at the gateway. The conversion module supports 315 OpenAPI services in the cloud and integrates MCP transport variants. Session-aware routing decouples the scalability of the gateway layer and the MCP service layer. The hybrid retrieval engine sustains $\sim$98\% Top-15 recall; it scales agent tool access to 3{,}000+ tools with improved tool selection accuracy. We also share the lessons learned from deploying the gateway system in production.

## Uber Builds MCP Gateway to Govern Access to 800+ Servers and 5,000+ AI Agent Tools

DevFeed: [Uber Builds MCP Gateway to Govern Access to 800+ Servers and 5,000+ AI Agent Tools](<https://devfeed.tech/articles/uber-builds-mcp-gateway-to-govern-access-to-800-servers-and-5-000-ai-agent-tools-112398.md>)

Original publisher: [Read original article](<https://www.infoq.com/news/2026/11/uber-mcp-gateway-ai-agents/>)

Author: Leela Kumili

Published: 2026-11-02T13:53:00Z

Content type: article

Language: en

Sources: [InfoQ](<https://devfeed.tech/sources/infoq.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [gateway](<https://devfeed.tech/topics/gateway.md>), [control-plane](<https://devfeed.tech/topics/control-plane.md>), [Authorization](<https://devfeed.tech/topics/authorization.md>), [Security](<https://devfeed.tech/topics/security.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [data loss prevention](<https://devfeed.tech/topics/data-loss-prevention.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-tools](<https://devfeed.tech/tags/agent-tools.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-ml-data-engineering](<https://devfeed.tech/tags/ai-ml-data-engineering.md>), [api](<https://devfeed.tech/tags/api.md>), [api-gateway](<https://devfeed.tech/tags/api-gateway.md>), [architecture-design](<https://devfeed.tech/tags/architecture-design.md>), [data](<https://devfeed.tech/tags/data.md>), [development](<https://devfeed.tech/tags/development.md>), [discovery](<https://devfeed.tech/tags/discovery.md>), [distributed-systems](<https://devfeed.tech/tags/distributed-systems.md>), [execution](<https://devfeed.tech/tags/execution.md>), [gateway](<https://devfeed.tech/tags/gateway.md>), [grpc](<https://devfeed.tech/tags/grpc.md>), [incremental](<https://devfeed.tech/tags/incremental.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [mcp-gateway](<https://devfeed.tech/tags/mcp-gateway.md>), [mcp-servers](<https://devfeed.tech/tags/mcp-servers.md>), [microservices](<https://devfeed.tech/tags/microservices.md>), [ml-data-engineering](<https://devfeed.tech/tags/ml-data-engineering.md>), [model-context-protocol-mcp](<https://devfeed.tech/tags/model-context-protocol-mcp.md>), [news](<https://devfeed.tech/tags/news.md>), [redaction](<https://devfeed.tech/tags/redaction.md>), [rest](<https://devfeed.tech/tags/rest.md>), [runtime](<https://devfeed.tech/tags/runtime.md>), [sensitive-data](<https://devfeed.tech/tags/sensitive-data.md>), [servers](<https://devfeed.tech/tags/servers.md>), [service-discovery](<https://devfeed.tech/tags/service-discovery.md>), [thrift](<https://devfeed.tech/tags/thrift.md>), [tools](<https://devfeed.tech/tags/tools.md>), [uber](<https://devfeed.tech/tags/uber.md>), [uber-mcp-gateway-ai-agents](<https://devfeed.tech/tags/uber-mcp-gateway-ai-agents.md>)

### AI overview

Uber's MCP Gateway provides a shared way for AI agents to discover and call internal APIs across more than 800 MCP servers and 5,000 tools. Its control-plane MCP Registry stores tool schemas, ownership and enablement settings; the runtime Proxy Gateway translates MCP requests to HTTP, gRPC or TChannel and returns MCP-compatible results. AutoCrawler generates tool schemas from Protocol Buffers and Thrift definitions, but discovered tools stay disabled until their owners approve them. Authorization applies at server and tool levels, with sensitive-response redaction; a separate service exchanges internal tokens for third-party credentials. Omni MCP supports search and incremental tool discovery, while Response Projection limits returned fields. The excerpt also notes that Uber's aifx CLI lets coding agents invoke tools and save results to files.

### Source excerpt

Uber has built an MCP Gateway to standardize how AI agents discover and invoke internal services across more than 800 MCP servers and 5,000 tools. The gateway separates tool registration from runtime execution and includes automated API discovery, access controls, sensitive data redaction, incremental tool discovery through Omni MCP, and response filtering. By Leela Kumili

## Amazon ECS Gateway Arrives with Generated Hostnames and No Custom Domain Support

DevFeed: [Amazon ECS Gateway Arrives with Generated Hostnames and No Custom Domain Support](<https://devfeed.tech/articles/amazon-ecs-gateway-arrives-with-generated-hostnames-and-no-custom-domain-support-111800.md>)

Original publisher: [Read original article](<https://www.infoq.com/news/2026/11/introducing-amazon-ecs-gateway/>)

Author: Steef-Jan Wiggers

Published: 2026-11-02T09:49:00Z

Content type: news

Language: en

Sources: [InfoQ](<https://devfeed.tech/sources/infoq.md>)

Topics: [gateway](<https://devfeed.tech/topics/gateway.md>), [Cloud Networking](<https://devfeed.tech/topics/cloud-networking.md>), [Amazon Web Services](<https://devfeed.tech/topics/aws.md>), [domain](<https://devfeed.tech/topics/domain.md>), [Amazon Route 53](<https://devfeed.tech/topics/amazon-route-53.md>)

Tags: [account](<https://devfeed.tech/tags/account.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [announcement](<https://devfeed.tech/tags/announcement.md>), [application](<https://devfeed.tech/tags/application.md>), [architecture-design](<https://devfeed.tech/tags/architecture-design.md>), [aws](<https://devfeed.tech/tags/aws.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [containers](<https://devfeed.tech/tags/containers.md>), [custom-domain](<https://devfeed.tech/tags/custom-domain.md>), [define](<https://devfeed.tech/tags/define.md>), [development](<https://devfeed.tech/tags/development.md>), [devops](<https://devfeed.tech/tags/devops.md>), [documentation](<https://devfeed.tech/tags/documentation.md>), [domain](<https://devfeed.tech/tags/domain.md>), [ecs](<https://devfeed.tech/tags/ecs.md>), [gateway](<https://devfeed.tech/tags/gateway.md>), [ingress](<https://devfeed.tech/tags/ingress.md>), [introducing-amazon-ecs-gateway](<https://devfeed.tech/tags/introducing-amazon-ecs-gateway.md>), [networking](<https://devfeed.tech/tags/networking.md>), [news](<https://devfeed.tech/tags/news.md>), [platform](<https://devfeed.tech/tags/platform.md>), [platform-teams](<https://devfeed.tech/tags/platform-teams.md>), [resource](<https://devfeed.tech/tags/resource.md>), [routing](<https://devfeed.tech/tags/routing.md>), [service](<https://devfeed.tech/tags/service.md>), [services](<https://devfeed.tech/tags/services.md>), [teams](<https://devfeed.tech/tags/teams.md>)

### AI overview

Amazon ECS Gateway lets platform teams configure ingress once, then application teams attach ECS services through a connector. ECS provisions each service a generated `https://<unique-id>.ecs.<region>.on.aws` hostname and routes requests by hostname through shared Application Load Balancers. The excerpt says the announcement and documentation do not describe custom domains, Route 53, or CNAME support; commenters note a CNAME would not resolve the host-based routing issue. Gateways are available in commercial ECS regions at no charge beyond provisioned resources. Each load balancer can serve 25 services; gateways add more as needed but do not consolidate partially filled ones, and each is billed. The gateway does not repair externally changed or deleted managed resources, which can interrupt traffic or cause later operations to fail. Services must use awsvpc networking in the same VPC and account, listeners support HTTPS on port 443, and Express Mode services are excluded. The excerpt describes a default maximum of 10 load balancers per gateway, configurable up to 200, with deployments failing if the limit is reached and none has capacity.

### Source excerpt

AWS has released Amazon ECS Gateway, an account-level ingress resource letting platform teams define networking once and application teams opt services in with a connector. Each service gets a generated hostname and routing is host-based, and neither the announcement nor the documentation covers custom domains. By Steef-Jan Wiggers

## MCP gateway vs policy enforcement: what's the difference?

DevFeed: [MCP gateway vs policy enforcement: what's the difference?](<https://devfeed.tech/articles/mcp-gateway-vs-policy-enforcement-what-s-the-difference-119452.md>)

Original publisher: [Read original article](<https://nirmata.com/2026/10/29/mcp-gateway-vs-policy-enforcement-whats-the-difference/>)

Author: Ritesh Patel

Published: 2026-10-29T23:00:00Z

Content type: article

Language: en

Sources: [Nirmata](<https://devfeed.tech/sources/nirmata.md>)

Topics: [Authorization](<https://devfeed.tech/topics/authorization.md>), [gateway](<https://devfeed.tech/topics/gateway.md>), [policy-as-code](<https://devfeed.tech/topics/policy-as-code.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-governance](<https://devfeed.tech/tags/ai-governance.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [gateway](<https://devfeed.tech/tags/gateway.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [mcp-gateway](<https://devfeed.tech/tags/mcp-gateway.md>), [policy](<https://devfeed.tech/tags/policy.md>), [policy-enforcement](<https://devfeed.tech/tags/policy-enforcement.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

An MCP gateway routes and logs tool traffic; policy enforcement makes the allow, deny, or hold decision for each call. A gateway enables enforcement only when calls pass through it and the developer cannot bypass it. Network gateways can cover routed HTTP servers, while local stdio servers run outside that path. Enforcement can also live in Claude Code's permission rules and hooks or on the server; server input validation, access controls, and HTTP token-audience checks remain necessary. For stronger controls, the excerpt recommends managed server allowlists, tool-specific deny rules, decision logs developers cannot edit, and tests on managed machines. Details matter: allowlists can merge with user settings unless `allowManagedMcpServersOnly` is true, tool deny rules depend on registered server names, and hooks may fail open unless configured to block.

### Source excerpt

An MCP gateway routes and logs tool traffic. Policy enforcement decides allow, deny or hold on each call. Here is how they differ and which one can stop a call.

## How to stop PII and national IDs from reaching LLMs

DevFeed: [How to stop PII and national IDs from reaching LLMs](<https://devfeed.tech/articles/how-to-stop-pii-and-national-ids-from-reaching-llms-119450.md>)

Original publisher: [Read original article](<https://nirmata.com/2026/10/29/how-to-stop-pii-and-national-ids-from-reaching-llms/>)

Author: Ritesh Patel

Published: 2026-10-29T19:00:00Z

Content type: tutorial

Language: en

Sources: [Nirmata](<https://devfeed.tech/sources/nirmata.md>)

Topics: [pii](<https://devfeed.tech/topics/pii.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [ner](<https://devfeed.tech/topics/ner.md>), [gateway](<https://devfeed.tech/topics/gateway.md>), [Regular expression](<https://devfeed.tech/topics/regular-expression.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-governance](<https://devfeed.tech/tags/ai-governance.md>), [block](<https://devfeed.tech/tags/block.md>), [checksums](<https://devfeed.tech/tags/checksums.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [claude-code-hooks](<https://devfeed.tech/tags/claude-code-hooks.md>), [data-protection](<https://devfeed.tech/tags/data-protection.md>), [gateway](<https://devfeed.tech/tags/gateway.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [ids](<https://devfeed.tech/tags/ids.md>), [llms](<https://devfeed.tech/tags/llms.md>), [ner](<https://devfeed.tech/tags/ner.md>), [pii](<https://devfeed.tech/tags/pii.md>), [security](<https://devfeed.tech/tags/security.md>), [stop](<https://devfeed.tech/tags/stop.md>)

### AI overview

Keep PII from reaching an LLM by checking prompts and tool results before they leave your network, using checksum recognizers for structured IDs and named-entity models for names, then redacting, holding or blocking matches. Coverage depends on checking each route: Claude Code's UserPromptSubmit can block but cannot rewrite typed prompts; PreToolUse can alter tool inputs, and PostToolUse can redact results only after the tool has run. A gateway can inspect model requests routed through it, but separate scripts or MCP servers may bypass it, and gateway redaction support must be verified. Presidio's Aadhaar recognizer is disabled by default and must be added explicitly; its checksum still allows about 10% of random 12-digit numbers through, so matches need review. Detection is not complete, and hook timeouts pass prompts unless onFailure is set to block. The excerpt recommends testing with synthetic valid and near-miss numbers, starting with redaction and review, and limiting agent file access.

### Source excerpt

Stop PII and national IDs reaching LLMs: detect them with checksums and NER, then redact, hold or block each match in Claude Code hooks or at a gateway.

## Zephyr RTOS 4.5 Now Available: Two New Architectures, Multimedia Pipelines, SBOMs for the CRA, and More

DevFeed: [Zephyr RTOS 4.5 Now Available: Two New Architectures, Multimedia Pipelines, SBOMs for the CRA, and More](<https://devfeed.tech/articles/zephyr-rtos-4-5-now-available-two-new-architectures-multimedia-pipelines-sboms-for-the-cra-and-more-106035.md>)

Original publisher: [Read original article](<https://zephyrproject.org/zephyr-rtos-4-5-now-available-two-new-architectures-multimedia-pipelines-sboms-and-more/>)

Author: Benjamin Cabé

Published: 2026-10-28T22:46:51Z

Content type: release

Language: en

Sources: [Zephyr Project](<https://devfeed.tech/sources/zephyr-project-2.md>)

Topics: [Zephyr RTOS](<https://devfeed.tech/topics/zephyr-rtos.md>), [cyber resilience act](<https://devfeed.tech/topics/cyber-resilience-act.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [gateway](<https://devfeed.tech/topics/gateway.md>), [Data pipelines](<https://devfeed.tech/topics/data-pipelines.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>), [Cryptography](<https://devfeed.tech/topics/cryptography.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [WebSocket](<https://devfeed.tech/topics/websocket.md>)

Tags: [announcements](<https://devfeed.tech/tags/announcements.md>), [architectures](<https://devfeed.tech/tags/architectures.md>), [blog](<https://devfeed.tech/tags/blog.md>), [cra](<https://devfeed.tech/tags/cra.md>), [debugging](<https://devfeed.tech/tags/debugging.md>), [faster](<https://devfeed.tech/tags/faster.md>), [hexagon](<https://devfeed.tech/tags/hexagon.md>), [improvements](<https://devfeed.tech/tags/improvements.md>), [multimedia](<https://devfeed.tech/tags/multimedia.md>), [network](<https://devfeed.tech/tags/network.md>), [network-stack](<https://devfeed.tech/tags/network-stack.md>), [pipelines](<https://devfeed.tech/tags/pipelines.md>), [release](<https://devfeed.tech/tags/release.md>), [rtos](<https://devfeed.tech/tags/rtos.md>), [sboms](<https://devfeed.tech/tags/sboms.md>), [testing](<https://devfeed.tech/tags/testing.md>), [zephyr](<https://devfeed.tech/tags/zephyr.md>)

### AI overview

Zephyr 4.5 adds TriCore and Hexagon support, broader networking, multimedia pipelines, and security and diagnostic features. Its network stack gains up to 21% TCP and 12% UDP throughput in deterministic QEMU loopback benchmarks; it also adds QUIC, HTTP/3 serving, SSH, and IPv4 forwarding with NAT. The experimental mpipe subsystem links source, transform, and sink elements, passing buffers without copies; a leaky queue lets video continue at full rate while slower inference skips frames. SPDX 3.0 SBOM generation records source files and build details, though SPDX 2.3 remains the default. Other additions include per-file assertion levels, heap error detection, trace viewing and export, UDP coredumps, expanded host-backed native_sim peripherals, and multi-device Twister tests. The release also adds six driver classes, 178 boards, and 29 shields. Upgrading from 4.4 may require changes for the ring buffer API and CMake flash/debug targets; TriCore QEMU and the Hexagon toolchain require separate setup.

### Source excerpt

Zephyr 4.5 brings two new architectures (TriCore and Hexagon), a faster and broader network stack, multimedia pipelines with mpipe, and a long list of debugging and testing improvements.

## How Uber Built A Gateway For AI Agents To Access Tools

DevFeed: [How Uber Built A Gateway For AI Agents To Access Tools](<https://devfeed.tech/articles/how-uber-built-a-gateway-for-ai-agents-to-access-tools-105340.md>)

Original publisher: [Read original article](<https://blog.bytebytego.com/p/how-uber-built-a-gateway-for-ai-agents>)

Author: ByteByteGo

Published: 2026-10-28T15:31:05Z

Content type: article

Language: en

Sources: [ByteByteGo](<https://devfeed.tech/sources/bytebytego.md>)

Topics: [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Tool](<https://devfeed.tech/topics/tool.md>), [gateway](<https://devfeed.tech/topics/gateway.md>)

Tags: [access-control](<https://devfeed.tech/tags/access-control.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-systems](<https://devfeed.tech/tags/agentic-systems.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-application](<https://devfeed.tech/tags/ai-application.md>), [ai-applications](<https://devfeed.tech/tags/ai-applications.md>), [ai-assistant](<https://devfeed.tech/tags/ai-assistant.md>), [api](<https://devfeed.tech/tags/api.md>), [apis](<https://devfeed.tech/tags/apis.md>), [arguments](<https://devfeed.tech/tags/arguments.md>), [auth](<https://devfeed.tech/tags/auth.md>), [authorization](<https://devfeed.tech/tags/authorization.md>), [backend](<https://devfeed.tech/tags/backend.md>), [gateway](<https://devfeed.tech/tags/gateway.md>), [tools](<https://devfeed.tech/tags/tools.md>), [uber](<https://devfeed.tech/tags/uber.md>)

### AI overview

Uber's MCP Gateway centralizes tool discovery, execution, and access controls across services that use different protocols. Its MCP Registry acts as a control plane for tool definitions and approvals; the Proxy Gateway handles requests and translates MCP arguments and results for backends such as gRPC, HTTP, and TChannel. AutoCrawler, powered by Cadence, builds catalog entries from existing API definitions or native MCP servers. Newly discovered tools remain disabled until their owners review and approve them. The gateway refreshes its in-memory configuration periodically, applies caller and tool-level access policies, and can redact sensitive response data. To manage a large catalog and reduce context use, Uber describes gradual discovery through Omni MCP, response projection, and Code Mode. The account is based on publicly shared details and notes that inaccuracies may be reported.

### Source excerpt

In this article, we'll look at how Uber built this gateway in detail.

## GLo-MAPPO: Multi-Agent Deep Reinforcement Learning for Energy-Efficient UAV-Assisted LoRa Networks

DevFeed: [GLo-MAPPO: Multi-Agent Deep Reinforcement Learning for Energy-Efficient UAV-Assisted LoRa Networks](<https://devfeed.tech/articles/glo-mappo-multi-agent-deep-reinforcement-learning-for-energy-efficient-uav-assisted-lora-networks-104183.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2509.17676>)

Author: Abdullahi Isa Ahmed, Jamal Bentahar, El Mehdi Amhoud

Published: 2026-10-28T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Networking](<https://devfeed.tech/sources/arxiv-networking.md>)

Topics: [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [gateway](<https://devfeed.tech/topics/gateway.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Deep learning](<https://devfeed.tech/topics/deep-learning.md>), [Internet of things](<https://devfeed.tech/topics/iot.md>)

Tags: [architecture](<https://devfeed.tech/tags/architecture.md>), [coverage](<https://devfeed.tech/tags/coverage.md>), [cs-ni](<https://devfeed.tech/tags/cs-ni.md>), [data](<https://devfeed.tech/tags/data.md>), [decentralized](<https://devfeed.tech/tags/decentralized.md>), [deep-reinforcement-learning](<https://devfeed.tech/tags/deep-reinforcement-learning.md>), [devices](<https://devfeed.tech/tags/devices.md>), [ee](<https://devfeed.tech/tags/ee.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [energy](<https://devfeed.tech/tags/energy.md>), [energy-efficiency](<https://devfeed.tech/tags/energy-efficiency.md>), [environments](<https://devfeed.tech/tags/environments.md>), [execution](<https://devfeed.tech/tags/execution.md>), [flora](<https://devfeed.tech/tags/flora.md>), [game](<https://devfeed.tech/tags/game.md>), [gateway](<https://devfeed.tech/tags/gateway.md>), [learning](<https://devfeed.tech/tags/learning.md>), [lora](<https://devfeed.tech/tags/lora.md>), [multi-agent](<https://devfeed.tech/tags/multi-agent.md>), [networks](<https://devfeed.tech/tags/networks.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>)

### AI overview

GLo-MAPPO treats UAVs as mobile LoRa gateways and jointly optimizes spreading factors, transmission power, UAV routes, and device associations to improve weighted system energy efficiency. It models the task as a partially observable stochastic game and uses PPO with centralized training and decentralized execution: training coordinates policies, while each UAV acts independently at runtime. The abstract reports better energy efficiency and lower power consumption than state-of-the-art multi-agent reinforcement-learning benchmarks across network densities, and describes closed-loop packet-level validation with OMNeT++/FLoRa. The excerpt does not provide quantitative results or details of the validation.

### Source excerpt

arXiv:2509.17676v3 Announce Type: replace Abstract: The rapid advancement of Low-Power Wide Area Networks (LPWANs), particularly Long Range (LoRa) technology, has positioned them as a cornerstone of Next-Generation Internet of Things (NG-IoT) applications. Despite their long-range and low-power advantages, achieving high energy efficiency (EE) in LoRa networks remains a significant challenge in highly dynamic environments. Traditional terrestrial gateway deployments often suffer from coverage gaps and non-line-of-sight (NLoS) propagation, while satellite-based alternatives incur excessive energy consumption and prohibitive latency. To address these limitations, we propose a multi-UAV architecture in which unmanned aerial vehicles (UAVs) serve as mobile LoRa gateways to dynamically collect data from LoRa end devices (EDs). We formulate a joint optimization problem to maximize the weighted system EE by jointly optimizing spreading factors, transmission powers, UAV trajectories, and ED-UAV associations. This problem is transformed into a partially observable stochastic game (POSG), which we solve using our proposed Green LoRa Multi-Agent Proximal Policy Optimization (GLo-MAPPO). We adopt PPO because its clipped surrogate objective discourages excessively large policy updates, thereby promoting stable learning as multiple UAV agents simultaneously adapt their behaviors. Combined with centralized training and decentralized execution (CTDE), this enables coordinated policy learning while allowing each UAV to make decisions independently during execution. Simulation results show that GLo-MAPPO consistently outperforms state-of-the-art multi-agent reinforcement learning (MARL) benchmarks in terms of EE and power consumption across varying network densities. We further validate the trained policy through closed-loop, packet-level co-simulation using the OMNeT++/FLoRa LoRa simulator. Finally, ....

[Next page](<https://devfeed.tech/topics/gateway.md?cursor=WyIyMDI2LTEwLTI4VDA0OjAwOjAwKzAwOjAwIiwgIjE0ZmI2ZTg2LTM3NTItNDJhMS05MDZhLTI0MmJiYTkzOTM3YSJd>)