# Model Context Protocol (MCP) An open protocol for connecting AI applications and language models to external data sources and tools. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## MCP Apps: Your UI, Their Chat DevFeed: [MCP Apps: Your UI, Their Chat]() Original publisher: [Read original article]() Author: James Strong Published: 2026-09-16T07:00:00Z Content type: article Language: en Sources: [Scott Logic]() Topics: [Model Context Protocol (MCP)](), [ui](), [ChatGPT](), [App]() Tags: [ai](), [app](), [artificial-intelligence](), [chatgpt](), [mcp](), [ui]() ### AI overview The article examines MCP Apps, an extension of the Model Context Protocol, alongside the protocol's 2026-07-28 changes. It explains how MCP Apps let servers return isolated, interactive, stateful UIs that clients such as ChatGPT can embed in agent responses, with examples including dashboards, data tables, and forms. ### Source excerpt A lot of focus has been put on the statelessness introduced as part of the new MCP specification, but the formalisation of extensions, including MCP Apps, is also worth attention. Using FastMCP and Prefab, I put together an MCP app and show it running in ChatGPT. ## Shared Selective Persistent Memory for Agentic LLM Systems DevFeed: [Shared Selective Persistent Memory for Agentic LLM Systems]() Original publisher: [Read original article]() Published: 2026-09-16T00:00:00Z Content type: article Language: en Sources: [Apple Machine Learning Research]() Topics: [Large Language Model](), [agent observability](), [Framework](), [Code](), [configuration](), [Access Control](), [Git](), [Model Context Protocol (MCP)](), [CSV](), [SQL](), [Grafana]() Tags: [access-control](), [agentic](), [agents](), [code](), [configuration](), [csv](), [dashboards](), [git](), [llm](), [mcp](), [memory](), [platform](), [replication](), [sql]() ### AI overview This research introduces shared selective persistent memory for agentic LLM systems. The architecture retains reusable task specifications, data schemas, tool configurations, and output constraints while discarding session-specific reasoning traces. Shared workspaces support role-based collaborative reuse, and experiments report higher task completion than no memory or full-history persistence, along with zero-token data refresh and lower token costs. ### Source excerpt Agentic LLM systems that generate code through multi-turn tool use face a fundamental context problem: each session starts from zero, discarding the configuration choices, domain constraints, data schemas, and tool-use patterns that made previous sessions productive. Naively persisting entire conversation histories is both token-inefficient and counterproductive--irrelevant context degrades generation quality. We introduce shared selective persistent memory, a memory architecture for agentic systems that identifies and retains four categories of reusable context--task specifications, data... ## Laravel MCP 1.0 Is Released DevFeed: [Laravel MCP 1.0 Is Released]() Original publisher: [Read original article]() Author: Eric L. Barnes Published: 2026-09-15T14:27:51Z Content type: release Language: en Sources: [Laravel]() Topics: [Laravel](), [Model Context Protocol (MCP)](), [OAuth](), [pkce](), [Caching](), [servers]() Tags: [caching](), [context-window](), [laravel](), [mcp](), [news](), [oauth](), [pkce](), [servers]() ### AI overview Laravel MCP 1.0 is the first stable release of Laravel's package for building Model Context Protocol servers. It adds protocol revision 2026-07-28 support, searchable tool catalogs, cache hints, stateless request handling, OAuth changes requiring PKCE, and Client ID Metadata Documents. ### Source excerpt Laravel MCP 1.0 ships protocol revision 2026-07-28, stateless servers, searchable tool catalogs, cache hints, and reworked OAuth with required PKCE. The post Laravel MCP 1.0 Is Released appeared first on Laravel News. Join the Laravel Newsletter to get Laravel articles like this directly in your inbox. ## Using the Komodo MCP Server to Manage Docker Infrastructure with AI Assistants DevFeed: [Using the Komodo MCP Server to Manage Docker Infrastructure with AI Assistants]() Original publisher: [Read original article]() Author: Brandon Lee Published: 2026-09-15T12:38:26Z Content type: tutorial Language: en Sources: [Virtualization Howto]() Topics: [Homelab](), [Model Context Protocol (MCP)](), [Docker](), [Docker Compose](), [GitOps](), [Artificial Intelligence]() Tags: [ai](), [automation](), [containers](), [docker](), [gitops](), [home-lab](), [home-server](), [infrastructure](), [mcp]() ### AI overview This tutorial introduces the Komodo MCP Server, which connects AI assistants such as Claude and GitHub Copilot to Komodo for managing Docker environments. It describes natural-language control of containers, stacks, deployments, servers, builds, repositories, and related infrastructure through the Model Context Protocol. ### Source excerpt There are so many cool projects now that we have access to in the the realm of home lab, especially when it comes to automation and AI Ops for our... The post I Gave AI Control of My Docker Home Lab With Komodo MCP appeared first on Virtualization Howto. ## Super Stack: Laravel Starter Kit With Filament and NativePHP DevFeed: [Super Stack: Laravel Starter Kit With Filament and NativePHP]() Original publisher: [Read original article]() Author: Yannick Lyn Fatt Published: 2026-09-15T02:50:55Z Content type: news Language: en Sources: [Laravel]() Topics: [Laravel](), [MCP](), [MCP Server](), [Model Context Protocol (MCP)](), [Open Source](), [PHP](), [Android](), [iOS]() Tags: [api](), [authentication](), [filament](), [github](), [laravel](), [laravel-packages](), [mcp](), [mcp-server](), [mobile](), [nativephp](), [open-source](), [starter-kits]() ### AI overview NativePHP released Super Stack, an open-source Laravel starter kit that combines a web app, Filament admin panel, native mobile app, Sanctum API tokens, and a Laravel MCP server in one repository. The MCP server is intended for local exploration and requires authentication before production deployment. ### Source excerpt Super Stack is an open-source Laravel starter kit from NativePHP with a Filament admin, a native mobile app, Sanctum, and a Laravel MCP server in one repo. The post Super Stack: Laravel Starter Kit With Filament and NativePHP appeared first on Laravel News. Join the Laravel Newsletter to get Laravel articles like this directly in your inbox. ## 🎙 How I AI: How two SpaceXAI designers use Grok Bot to do their jobs DevFeed: [🎙 How I AI: How two SpaceXAI designers use Grok Bot to do their jobs]() Original publisher: [Read original article]() Author: Lenny Rachitsky Published: 2026-09-14T15:03:48Z Content type: article Language: en Sources: [Lenny's Newsletter]() Topics: [Artificial Intelligence](), [Bot](), [Figma](), [Model Context Protocol (MCP)](), [Google]() Tags: [agents](), [ai](), [ai-agents](), [designers](), [figma](), [google](), [mcp](), [podcast]() ### AI overview This podcast episode features SpaceXAI designers John Bai and Peng Zheng describing how they use Grok Bot and AI agents in their design work. Peng demonstrates a self-updating personal site whose workflow handles location lookup, custom 3D artwork, and publishing. John describes using voice memos, Figma, and an MCP connection to create design assets and prototypes. ### Source excerpt Your weekly listens from How I AI, part of the Lenny's Podcast Network ## Deploy, Discover, Inspect, Observe: A Summer Spent Making a Public Vespa MCP Server DevFeed: [Deploy, Discover, Inspect, Observe: A Summer Spent Making a Public Vespa MCP Server]() Original publisher: [Read original article]() Author: eivinbingen oystein viktor mfstort Published: 2026-09-13T00:00:00Z Content type: article Language: en Sources: [Vespa Blog]() Topics: [Model Context Protocol (MCP)](), [MCP Server](), [Cloud](), [AI Agent](), [Large Language Model](), [Command-line interface]() Tags: [ai-agent](), [ai-assistants](), [claude](), [cli](), [cloud](), [codex](), [internships](), [language-models](), [mcp](), [mcp-server]() ### AI overview This article describes the construction of a standalone, publicly hosted Vespa Cloud MCP server. It explains how MCP connects AI assistants and language models to external systems through resources, tools, and prompts, and discusses evaluating MCP usage against terminal access and Vespa CLI access. ### Source excerpt We built a standalone Vespa Cloud MCP server as a summer interns project ## Agent Plugins package your skills, tools, and more DevFeed: [Agent Plugins package your skills, tools, and more]() Original publisher: [Read original article]() Author: Kevin Hou; Haoyu Wang; Alan Blount Published: 2026-09-12T11:04:33.891311Z Content type: article Language: en Sources: [Google Developers Blog]() Topics: [Agent Skills](), [Model Context Protocol (MCP)](), [MCP Server](), [Google](), [amazon](), [Microsoft](), [OpenAI](), [Vercel]() Tags: [agent-skills](), [amazon](), [google](), [maintainers](), [manifest](), [mcp](), [mcp-server](), [microsoft](), [openai](), [plugin](), [portable](), [skills](), [vercel]() ### AI overview The article introduces Agent Plugins 1.0.0, a vendor-neutral specification for packaging Agent Skills and MCP servers into portable plugins. It standardizes the manifest and directory layout so developers can distribute one package across clients while preserving client-specific flexibility. Google is joining the Core Maintainers and beginning support in its products. ### Source excerpt Agent Plugins 1.0.0 is a new, vendor-neutral directory specification--backed by Google, Amazon, Microsoft, and others--for packaging Agent Skills and MCP servers into a single portable unit. By standardizing the manifest (plugin.json) and utilizing a fixed directory layout, it eliminates the need for developers to maintain separate wrappers or configurations to support different AI coding agents and IDEs. Google has officially joined as a Core Maintainer and already rolled out support in the Agents CLI and Data Agent Kit, allowing developers to start building and distributing interoperable plugins today. ## Bringing custom knowledge to agents with AutoRAG DevFeed: [Bringing custom knowledge to agents with AutoRAG]() Original publisher: [Read original article]() Author: Diego Alvarez Ponce, Diego Garcia Perez Published: 2026-09-11T13:01:50Z Content type: article Language: en Sources: [Red Hat](), [Red Hat Developer]() Topics: [Retrieval Augmented Generation (RAG)](), [Model Context Protocol (MCP)](), [Databases](), [Large Language Model](), [AI Development](), [LLM evaluation / benchmarking]() Tags: [ai](), [ai-inference](), [artificial-intelligence](), [database](), [developer](), [generative-ai](), [gpu](), [guide](), [how-to](), [large-language-models-llms](), [model-context-protocol-mcp](), [rag](), [red-hat](), [terminal]() ### AI overview This guide explains how to use AutoRAG in Red Hat OpenShift AI to optimize retrieval-augmented generation for enterprise, domain-specific data. It also shows how to integrate a Model Context Protocol server that retrieves customer information from an internal database, using a fictional banking scenario. ### Source excerpt The large language models (LLMs) that power generative AI work by drawing upon the patterns and information present in their training data. Without access to the right data, LLMs struggle to comprehend context--like our internal corporate vocabulary--and as a result, start to hallucinate. The post Bringing custom knowledge to agents with AutoRAG appeared first on Red Hat Developer. ## Your tools work. Will the agent use them right? DevFeed: [Your tools work. Will the agent use them right?]() Original publisher: [Read original article]() Author: Gil Levin Published: 2026-09-10T00:00:00Z Content type: article Language: en Sources: [Webflow Blog]() Topics: [Model Context Protocol (MCP)](), [Artificial Intelligence](), [Claude Code](), [cursor]() Tags: [ai-agents](), [chatgpt](), [claude-code](), [cursor](), [engineering](), [mcp](), [tools]() ### AI overview Webflow's MCP eval harness tests whether autonomous agents use its tools correctly to complete plain-English, multi-step tasks. It runs Claude Code or OpenAI's Codex CLI against disposable Webflow sites, combines deterministic checks with LLM and visual judging, and sends traces and scores to Datadog. ### Source excerpt A passing MCP tool test tells you the JSON is valid. It doesn't tell you an agent will pick the right tool, in order, and get the task right. ## Why MCP security is about permissions overhaul DevFeed: [Why MCP security is about permissions overhaul]() Original publisher: [Read original article]() Author: Mohit Bansal Published: 2026-09-09T00:00:00Z Content type: article Language: en Sources: [Webflow Blog]() Topics: [Model Context Protocol (MCP)](), [Authorization](), [AI Agent](), [anthropic](), [GitHub]() Tags: [agent](), [ai](), [ai-agent](), [anthropic](), [github](), [identity](), [infrastructure](), [mcp](), [prompt-injection](), [security](), [server]() ### AI overview MCP security failures often arise from over-scoped credentials and weak permission boundaries rather than protocol bugs. The article examines prompt injection, tool poisoning, and confused deputy risks, and argues for redesigning access around the minimum permissions each task requires. ### Source excerpt Most MCP breaches trace back to over-scoped credentials, not broken code. Here's what a real permissions redesign checks for. ## One Tool, three surfaces: from an OpenAPI file to an MCP server, without writing it twice DevFeed: [One Tool, three surfaces: from an OpenAPI file to an MCP server, without writing it twice]() Original publisher: [Read original article]() Author: Hal Tyk's tutorial bot Published: 2026-09-07T09:27:00Z Content type: tutorial Language: en Sources: [Tyk API Management]() Topics: [OpenAPI Specification](), [Model Context Protocol (MCP)](), [MCP Server](), [API](), [ASCII](), [HTTP](), [cURL]() Tags: [ai-gateway](), [ai-governance](), [ai-readiness](), [ai-studio](), [api](), [api-management](), [api-platform-teams](), [article](), [ascii](), [curl](), [developer](), [http](), [llm-governance](), [llm-observability](), [mcp-server](), [model-context-protocol](), [openapi]() ### AI overview This tutorial shows how to define an HTTP API once in an OpenAPI document and expose it through three surfaces: model-initiated tool calls, a REST endpoint accessed with curl, and an MCP server. It uses the public Frankfurter foreign exchange API and explains import requirements such as OpenAPI 3.x, a complete servers URL, operationId values for every operation, and plain ASCII. ### Source excerpt Hello. I'm Hal, Tyk's tutorial bot, and today I have been given a genuinely satisfying assignment. We are going to describe an ordinary HTTP API once, in an OpenAPI document, and then use it three entirely different ways without touching that description again. A model will call it on its own initiative inside a chat. [...] The post One Tool, three surfaces: from an OpenAPI file to an MCP server, without writing it twice appeared first on Tyk API Management. ## Build an AI Agent (From Scratch) DevFeed: [Build an AI Agent (From Scratch)]() Original publisher: [Read original article]() Author: Nicolas Fränkel Published: 2026-09-06T00:00:00Z Content type: opinion Language: en Sources: [Nicolas Fränkel]() Topics: [AI Agent](), [Large Language Model](), [Model Context Protocol (MCP)](), [Retrieval Augmented Generation (RAG)](), [Multi Agent Systems]() Tags: [ai](), [ai-agent](), [ai-agents](), [book](), [claude-code](), [coding-assistant](), [genealogy](), [llm](), [llms](), [mcp](), [multi-agent-systems](), [rag](), [review]() ### AI overview A review of Build an AI Agent (From Scratch) by Jungjun Hur and Younghee Song describes the book's coverage of LLM agents, tool use, ReAct agents, RAG, memory, planning, code execution, multi-agent systems, and agent evaluation. The reviewer considers it a fundamental introduction, while wishing the evaluation chapter were more developed. ### Source excerpt Facts 10 chapters$29.29 (at the time of this writing)315 pages Chapters Building your first LLM agentWhat is an AI agent? ## MCP Went Stateless: What Now? DevFeed: [MCP Went Stateless: What Now?]() Original publisher: [Read original article]() Author: Janet Wagner Published: 2026-09-03T07:00:00Z Content type: article Language: en Sources: [Nordic APIs]() Topics: [Model Context Protocol (MCP)](), [Scalability](), [MCP Server](), [Architecture & Design](), [Security](), [Tool]() Tags: [ai](), [ai-agents](), [api-gateway](), [api-security](), [api-standards](), [artificial-intelligence](), [blog](), [cloud-native](), [developers](), [http](), [llm](), [mcp](), [mcp-server](), [model-context-protocol](), [scalability](), [security](), [strategy]() ### AI overview The article examines the shift to stateless MCP and its implications for scalability, state management, security, gateways, and MCP server architecture. ### Source excerpt The latest release of the Model Context Protocol (MCP) specification has created a lot of buzz in tech circles. Why? Primarily because this AI communication protocol has now gone stateless! This shift from stateful to stateless impacts how developers of MCP servers and AI tools use the protocol moving forward. In addition, the change impacts ... ## What is MCP authorization? How OAuth works for AI agents DevFeed: [What is MCP authorization? How OAuth works for AI agents]() Original publisher: [Read original article]() Author: WorkOS Published: 2026-09-03T00:00:00Z Content type: tutorial Language: en Sources: [WorkOS Blog]() Topics: [Model Context Protocol (MCP)](), [OAuth](), [MCP Server](), [AI Agent](), [Authorization](), [Authentication]() Tags: [agents](), [authentication](), [authorization](), [discovery](), [mcp](), [oauth](), [scopes](), [token]() ### AI overview This tutorial explains MCP authorization as an OAuth 2.1 flow for allowing AI agents to call protected MCP servers on a user's behalf. It covers the roles of the MCP server, client, and authorization server; audience-bound tokens; discovery; deprecated Dynamic Client Registration; and step-up authorization for additional scopes. ### Source excerpt MCP authorization is the OAuth 2.1 flow that lets an AI agent call a protected MCP server on a user's behalf. Here is how it works, step by step, under the 2026-07-28 spec. ## Meet the Symfony Core Team at the API Platform Conference 2026! DevFeed: [Meet the Symfony Core Team at the API Platform Conference 2026!]() Original publisher: [Read original article]() Author: Cécile HAMEREL Published: 2026-09-02T14:30:00Z Content type: news Language: en Sources: [Symfony Blog]() Topics: [API](), [Symfony](), [PHP](), [migration](), [Domain-driven design (DDD)](), [JSON Web Tokens](), [OAuth 2.0](), [OpenID connect (OIDC)](), [Model Context Protocol (MCP)]() Tags: [2026](), [ai-agents](), [api-platform](), [conference](), [event](), [mcp](), [migration](), [oauth2](), [oidc](), [php](), [symfony]() ### AI overview The API Platform Conference 2026 will take place in Lille, France, on September 17-18. The event will feature nearly 30 talks, including sessions by Symfony Core Team members on migration, API security, DDD, HTTP headers, FrankenPHP, AI agents, and MCP. ### Source excerpt The API Platform Conference, the international event dedicated to the API Platform framework and its ecosystem, will take place in two weeks in Lille, France, on September 17-18, 2026. Nearly 30 talks are scheduled, in both French and English, covering... ## Agents babysitting agents DevFeed: [Agents babysitting agents]() Original publisher: [Read original article]() Author: WorkOS Published: 2026-08-31T18:26:02Z Content type: opinion Language: en Sources: [WorkOS Blog]() Topics: [Development](), [AI-assisted coding](), [Pull Request](), [Claude Code](), [Model Context Protocol (MCP)](), [Terminal](), [Monitoring](), [cursor]() Tags: [agent](), [agents](), [claude](), [claude-code](), [coding-agents](), [cursor](), [mcp](), [monitoring](), [pull-request](), [review](), [terminal](), [tests]() ### AI overview WorkOS engineers describe using one coding agent to supervise another after pull requests are opened, with headless monitoring, narrowly scoped jobs, visible costs, protected credentials, and human approval for merging. ### Source excerpt How WorkOS engineers make agents babysitting agents safe: a headless surface to supervise through, scoped jobs, visible costs, and a human on the merge button. ## From Isolated Agents to Collective Intelligence: Why A2A Is the Protocol the Agentic SOC Has Been Waiting For DevFeed: [From Isolated Agents to Collective Intelligence: Why A2A Is the Protocol the Agentic SOC Has Been Waiting For]() Original publisher: [Read original article]() Author: Jeff Yeo Published: 2026-08-28T15:00:11Z Content type: article Language: en Sources: [Security @ Cisco Blogs]() Topics: [Agentic SOC](), [Model Context Protocol (MCP)](), [Security](), [Architecture & Design]() Tags: [agentic](), [agentic-ai](), [agentic-soc](), [agents](), [announcement](), [architecture](), [artificial-intelligence-ai](), [integration](), [mcp](), [mcp-server](), [model-context-protocol](), [security](), [workflow]() ### AI overview This article presents A2A as a protocol for enabling agents from different vendors and platforms to hand work to one another in a multi-agent security operations center. It explains that A2A complements MCP: MCP connects agents to data and tools, while A2A connects agents to other agents. The article describes this as a conceptual architecture because production security-agent handoffs mediated by A2A are not yet shipping. ### Source excerpt The Agentic SOC needs two protocols, not one. Learn how MCP and A2A work together as the vertical and horizontal layers of multi-agent security operations ## Webflow is now available in Codex and ChatGPT DevFeed: [Webflow is now available in Codex and ChatGPT]() Original publisher: [Read original article]() Author: Blaire McClure Published: 2026-08-24T00:00:00Z Content type: release Language: en Sources: [Webflow Blog]() Topics: [webflow](), [ChatGPT](), [codex](), [Model Context Protocol (MCP)](), [Artificial Intelligence](), [Content Management System](), [Accessibility](), [Search engine optimization (SEO)]() Tags: [accessibility](), [agents](), [chatgpt](), [code](), [codex](), [developer](), [extensions](), [links](), [mcp](), [optimization](), [performance](), [seo](), [skills](), [software](), [webflow]() ### AI overview Webflow is now available in Codex and ChatGPT through Webflow MCP, expanding access to Webflow sites and workflows. Built-in Skills can help users audit sites, manage CMS content, validate custom code, and accelerate development tasks using natural-language requests. ### Source excerpt Webflow is now available in Codex, alongside a new set of built-in Skills for both ChatGPT and Codex. ## MCP vs API: How they work together and when to use each DevFeed: [MCP vs API: How they work together and when to use each]() Original publisher: [Read original article]() Author: Jacob Schmitt Published: 2026-08-20T21:30:00Z Content type: tutorial Language: en Sources: [The CircleCI Blog Feed | CircleCI]() Topics: [Model Context Protocol (MCP)](), [API](), [Artificial Intelligence]() Tags: [agents](), [ai-development](), [api](), [mcp](), [mcp-vs-api](), [mcp-vs-rest](), [when-to-use-mcp-vs-api](), [will-mcp-replace-apis]() ### AI overview This tutorial explains how APIs and the Model Context Protocol differ and work together. APIs expose operations for software to call, while MCP provides a standardized way for AI applications to discover and invoke selected capabilities at runtime, often through existing REST, GraphQL, or RPC interfaces. ### Source excerpt An API exposes operations software can call. MCP lets AI agents discover and invoke them at runtime. Learn how the two work together, and when to use each. ## Okta Cross App Access (XAA / ID-JAG) in Nirmata AIControls: standards-based authorization for AI agents DevFeed: [Okta Cross App Access (XAA / ID-JAG) in Nirmata AIControls: standards-based authorization for AI agents]() Original publisher: [Read original article]() Author: Ritesh Patel Published: 2026-08-19T00:24:40Z Content type: article Language: en Sources: [Nirmata]() Topics: [cross-app-access](), [Authorization](), [okta](), [Artificial Intelligence](), [Model Context Protocol (MCP)](), [Large Language Model](), [JSON Web Tokens](), [OAuth]() Tags: [ai](), [authorization](), [cross-app-access](), [engineering](), [jwt](), [llm](), [mcp](), [mcp-server](), [oauth](), [okta](), [standards]() ### AI overview The article explains how Nirmata AIControls supports Okta Cross App Access and the ID-JAG authorization profile for AI agents. It describes token exchanges performed on behalf of agents, administrator-controlled app-to-app access, policy checks, budgets, and audit records for delegated MCP and LLM calls. ### Source excerpt AIControls now performs the ID-JAG token exchanges on your agents' behalf -- so agents need no protocol code -- and policy-checks, budgets, and attributes every delegated MCP and LLM call to the human it acts for. ID-JAG answers may this agent act for this user? AIControls answers what... The post Okta Cross App Access (XAA / ID-JAG) in Nirmata AIControls: standards-based authorization for AI agents first appeared on Nirmata. ## Is MCP Stateless or Stateful? DevFeed: [Is MCP Stateless or Stateful?]() Original publisher: [Read original article]() Author: Roger Perkin Published: 2026-08-14T06:51:31Z Content type: article Language: en Sources: [Roger Perkin Network Automation Consultant]() Topics: [Model Context Protocol (MCP)](), [Load Balancing]() Tags: [2026](), [architecture](), [faq](), [load-balancing](), [mcp](), [protocol](), [stateful](), [stateless]() ### AI overview The article states that MCP became stateless in version 2026-07-28, whereas the original release was stateful. It says requests are self-describing and independent, eliminating the need for connection handshakes, session IDs, and sticky load balancing. ### Source excerpt As of version 2026-07-28 the MCP protocol is now stateless. The original release was stateful. Every request is self-describing and independent, removing the need for connection handshakes, session IDs, or sticky load balancing. You can read all the important updates here: https://modelcontextprotocol.io/docs/2026-07-28/learn/architecture ## How Harness Built an MCP Gateway for AI Chat Access to GitHub, Jira, and Confluence DevFeed: [How Harness Built an MCP Gateway for AI Chat Access to GitHub, Jira, and Confluence]() Original publisher: [Read original article]() Author: Vivek Dixit Published: 2026-08-14T00:00:00Z Content type: article Language: en Sources: [Harness Blog]() Topics: [AI Chat](), [Model Context Protocol (MCP)](), [Authorization](), [GitHub](), [cloud-infrastructure]() Tags: [ai](), [engineering](), [github](), [mcp](), [mcp-gateway](), [platform](), [security](), [systems](), [third-party]() ### AI overview Harness describes building an MCP Gateway that lets Harness AI Chat access GitHub, Jira, and Confluence through a single governed interface. The gateway uses Harness RBAC, Secret Manager, and Connectors to control access and credentials while supporting distributed operation without dropped sessions. ### Source excerpt One MCP Gateway lets AI Chat call GitHub, Jira, and Confluence with per-tool permissions, RBAC visibility, and no dropped sessions at scale. | Blog ## Build a financial analysis MCP server with Appwrite Functions DevFeed: [Build a financial analysis MCP server with Appwrite Functions]() Original publisher: [Read original article]() Author: Aditya Oberai Published: 2026-08-06T00:00:00Z Content type: tutorial Language: en Sources: [Appwrite Blog]() Topics: [Appwrite](), [Model Context Protocol (MCP)](), [MCP Server](), [Database](), [Authorization]() Tags: [build](), [configuration](), [github](), [mcp](), [mcp-server](), [scopes](), [tutorials]() ### AI overview This tutorial explains how to build a financial analysis MCP server with Appwrite Functions. The example uses Appwrite MCP server tooling to create a TablesDB schema and dummy financial data, then deploys a read-only reporting server that can generate statements, summarize portfolios, analyze spending, calculate cash flow, and search transactions. ### Source excerpt Learn how to build a financial analysis MCP server with Appwrite Functions, TablesDB, and custom tools for statements, cash flow, and portfolio insights. [Next page]()