# Service Discovery Published articles for Service Discovery. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## 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]() Original publisher: [Read original article]() Author: Leela Kumili Published: 2026-11-02T13:53:00Z Content type: article Language: en Sources: [InfoQ]() Topics: [AI Agent](), [gateway](), [control-plane](), [Authorization](), [Security](), [AI Infrastructure](), [data loss prevention]() Tags: [agent](), [agent-tools](), [agents](), [ai](), [ai-agent](), [ai-ml-data-engineering](), [api](), [api-gateway](), [architecture-design](), [data](), [development](), [discovery](), [distributed-systems](), [execution](), [gateway](), [grpc](), [incremental](), [infrastructure](), [mcp](), [mcp-gateway](), [mcp-servers](), [microservices](), [ml-data-engineering](), [model-context-protocol-mcp](), [news](), [redaction](), [rest](), [runtime](), [sensitive-data](), [servers](), [service-discovery](), [thrift](), [tools](), [uber](), [uber-mcp-gateway-ai-agents]() ### 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 ## A Negotiation-Aware Hybrid LLM Framework for Intent Interpretation and Service Discovery DevFeed: [A Negotiation-Aware Hybrid LLM Framework for Intent Interpretation and Service Discovery]() Original publisher: [Read original article]() Author: Wided Meflah, Hayet Brabra, Walid Gaaloul Published: 2026-10-30T04:00:00Z Content type: article Language: en Sources: [arXiv: Artificial Intelligence](), [arXiv: Software Engineering]() Topics: [Large Language Model](), [Emerging Cloud Service Models]() Tags: [cloud](), [cs-ai](), [cs-se](), [detection](), [discovery](), [framework](), [matching](), [natural-language](), [negotiation](), [offers](), [service-discovery](), [services](), [structured](), [template](), [user](), [users]() ### AI overview The framework turns incomplete or conflicting natural-language cloud requests into provider-independent TOSCA templates, then finds candidate offers by deterministic matching against provider catalogs. It uses iterative natural-language negotiation to resolve conflicts detected during interpretation and requirements that prove unsatisfiable during discovery. In an evaluation of 70 diverse intents, it improved recall and F1 for conflict detection and service discovery versus single-shot and enhanced-prompting baselines, eliminated hallucinated offers, and resolved conflicts at a cost proportional to their number. The excerpt does not provide metric values or further evaluation details. ### Source excerpt arXiv:2610.40161v1 Announce Type: cross Abstract: Increasingly, users express their needs as natural-language intents rather than structured requests. These intents may be incomplete, high-level, or internally conflicting. A conflicting intent either violates fundamental properties of the cloud paradigm or states mutually inconsistent requirements. Classical composition approaches are designed for structured, low-level, and complete requests. They cannot interpret such intents, discover suitable services from provider catalogs, or negotiate conflicting requirements with users. To address this gap, we propose a negotiation-aware framework for intent interpretation and service discovery. The framework first refines the natural-language intent and dynamically detects conflicts. It then structures the intent into a provider-independent TOSCA template. For each specification, it retrieves candidate service offers through deterministic matching grounded in cloud provider offerings. Some conflicts arise during interpretation. Other requirements prove unsatisfiable during discovery. Both are resolved through iterative natural-language negotiation with the user. We evaluate the framework on 70 diverse intents against single-shot and enhanced-prompting baselines. It improves recall and F1 for both conflict detection and service discovery. It also eliminates hallucinated offers and resolves conflicts at a cost proportional to their number. ## Service Discovery: Types, Benefits & How It Works DevFeed: [Service Discovery: Types, Benefits & How It Works]() Original publisher: [Read original article]() Author: Ekakshar Published: 2026-10-28T09:42:53Z Content type: article Language: en Sources: [Talent500]() Topics: [CoreDNS Kubernetes](), [service-mesh](), [Cloud Architecture](), [implementation](), [observability]() Tags: [access-control](), [apache-zookeeper](), [api-gateway](), [authentication](), [backend](), [balancing](), [cache](), [client-side-service-discovery](), [cloud-native-applications](), [cluster](), [communication](), [microservices](), [server-side-service-discovery](), [service-discovery](), [service-discovery-in-microservices](), [service-discovery-tools](), [service-discovery-vs-load-balancing](), [service-registry](), [technology]() ### AI overview Service discovery lets applications find current service instances as infrastructure changes, replacing hardcoded addresses with registration, lookup, health monitoring, and routing. In client-side discovery, each application retrieves endpoints and selects an instance, gaining routing control but requiring discovery logic and handling of stale data. In server-side discovery, a proxy, gateway, or load balancer selects the destination, simplifying clients while adding routing infrastructure and potentially another network hop. Kubernetes Services and DNS provide stable in-cluster names; Consul supports discovery across varied environments; Eureka is commonly used with Spring ecosystems and client-side discovery; Istio adds mesh traffic management, security, and observability; ZooKeeper is a general coordination system that may need extra discovery logic. Discovery can supply destinations for load balancing but does not itself ensure resilience: health checks, timeouts, careful retries, and failure handling matter, and discovery cannot create capacity when all instances fail. ### Source excerpt Discover how Service Discovery enables applications in distributed systems and microservices architectures to locate and communicate with services dynamically. Explore its types, working mechanisms, tools, benefits, and implementation approaches for building scalable, resilient, and reliable applications. The post Service Discovery: Types, Benefits & How It Works appeared first on Talent500 blog.