# MCP MCP (Model Context Protocol) is an open-source standard for connecting AI applications to external systems. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Cypress Cloud MCP adds test details, filters, and compact responses DevFeed: [Cypress Cloud MCP adds test details, filters, and compact responses]() Original publisher: [Read original article]() Published: 2026-09-15T16:21:48Z Content type: release Language: en Sources: [Cypress Blog]() Topics: [Cypress](), [MCP](), [Test coverage]() Tags: [cypress](), [mcp](), [release](), [responses](), [september-2026]() ### AI overview Cypress Cloud MCP now provides compact responses by default, new per-spec and per-test tools, filters by run, spec, and test status, and duration data across multiple levels. It also adds deeper links for accessibility and UI coverage reports. ### Source excerpt New tools, more data, smaller responses: what's new in Cypress Cloud MCP as of September 2026. ## 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. ## 4 Speculative Decoding Variants DevFeed: [4 Speculative Decoding Variants]() Original publisher: [Read original article]() Author: Avi Chawla Published: 2026-09-12T20:03:46Z Content type: article Language: en Sources: [Daily Dose of Data Science]() Topics: [dynatrace](), [MCP](), [MCP Server](), [Traces](), [Latency]() Tags: [coding-agents](), [dynatrace](), [latency](), [mcp](), [mcp-server](), [traces]() ### AI overview This article explains how Dynatrace's open-source MCP server and related skills bring production traces and logs into coding agents for performance investigations. It also introduces speculative decoding, in which a cheaper drafter proposes tokens and a target model verifies them in parallel, then outlines variants based on how drafts are produced. ### Source excerpt ...covered with tradeoffs in production. ## A better way to build MCP servers with Laravel DevFeed: [A better way to build MCP servers with Laravel]() Original publisher: [Read original article]() Author: Pushpak Chhajed Published: 2026-09-11T12:01:00Z Content type: article Language: en Sources: [Laravel Blog]() Topics: [MCP](), [Laravel](), [MCP Server](), [context window](), [JSON Schema](), [Cloudflare]() Tags: [cloudflare](), [context-window](), [json-schema](), [laravel](), [mcp](), [mcp-server]() ### AI overview The article explains how Laravel MCP 1.0 uses searchable tool catalogs to avoid loading every MCP tool definition into an agent's context on every request. It describes the context costs of large tool surfaces and the evolution of the author's implementation. ### Source excerpt Every MCP tool loads on every request. Laravel MCP 1.0 fixes that with searchable tool catalogs: the same payload for 10 or 100 tools. ## AI, Disruption, and Standards DevFeed: [AI, Disruption, and Standards]() Original publisher: [Read original article]() Author: L. Jeffrey Zeldman Published: 2026-09-10T16:12:17Z Content type: opinion Language: en Sources: [Jeffrey Zeldman]() Topics: [Artificial Intelligence](), [ai-governance](), [web-standards](), [Generative AI](), [MCP](), [a2ui](), [Accessibility]() Tags: [a2ui](), [accessibility](), [ai](), [ai-governance](), [appearances](), [architecture](), [best-practices](), [design](), [designers](), [ethics](), [formats](), [generative-ai](), [governance](), [mcp](), [open-source](), [standards](), [ux](), [video](), [web-standards](), [webstandards]() ### AI overview This article introduces a video panel on AI and standards featuring Jeffrey Zeldman and Patrick Neeman. The discussion connects lessons from the web standards movement to AI interfaces, focusing on fragmented user experiences, accessibility, interoperability, provenance, and the role of open-source and community efforts. ### Source excerpt Individually, we have very little power, but together we have a great deal of power. In response to a series of Medium articles by Patrick Neeman--like this one that addressed issues of AI governance, fairness, and standardization--publisher Louis Rosenfeld invited Patrick and me to come on his show and talk about AI and standards. A [...] The post AI, Disruption, and Standards appeared first on Jeffrey Zeldman Presents. ## Three identity vendors shipped the same agent access pattern in eight days DevFeed: [Three identity vendors shipped the same agent access pattern in eight days]() Original publisher: [Read original article]() Author: WorkOS Published: 2026-09-04T16:24:43Z Content type: article Language: en Sources: [WorkOS Blog]() Topics: [Auth0](), [Authorization](), [MCP](), [OpenID connect (OIDC)](), [Single sign-on (SSO)](), [Model Context Protocol]() Tags: [anthropic-claude](), [api](), [auth0](), [authorization](), [cross-app-access](), [identity](), [mcp](), [oidc](), [okta](), [sso]() ### AI overview Okta, Auth0, and Descope shipped implementations of the Cross App Access agent-access pattern between August 24 and September 1. The pattern uses a Client ID Metadata Document to identify calling software and an ID-JAG token exchange to let an identity provider control application access. ### Source excerpt Okta, Auth0, and Descope all shipped Cross App Access between August 24 and September 1. The two-layer pattern underneath it outlasts whichever vendor wins. ## How AI Agents Discover and Integrate Public APIs DevFeed: [How AI Agents Discover and Integrate Public APIs]() Original publisher: [Read original article]() Author: Anthony Viard Published: 2026-09-02T16:00:00Z Content type: article Language: en Sources: [Postman Blog]() Topics: [AI Agent](), [API](), [Postman](), [MCP]() Tags: [ai-agent](), [ai-agents](), [api](), [api-discovery](), [apis](), [general](), [integration](), [mcp](), [model-context-protocol](), [orbit]() ### AI overview The article presents Orbit by Postman, which lets developers and AI agents discover public API endpoints by describing a desired workflow in plain language. Orbit evaluates endpoint capabilities, identifies gaps, and generates integration details such as authentication, URLs, parameters, response shapes, execution order, and implementation pitfalls. It can be accessed through search and integration endpoints or via the Model Context Protocol (MCP). ### Source excerpt I couldn't name the API my feature needed. Orbit found it in one search, then handed me the request bodies and the three bugs I'd have shipped. The post How AI Agents Discover and Integrate Public APIs appeared first on Postman Blog. ## WorkOS announces Agent Registration, Airlock, Relay, and native iOS and Android SDKs DevFeed: [WorkOS announces Agent Registration, Airlock, Relay, and native iOS and Android SDKs]() Original publisher: [Read original article]() Author: WorkOS Published: 2026-09-02T00:00:00Z Content type: release Language: en Sources: [WorkOS Blog]() Topics: [SDKs](), [Android](), [iOS](), [Authorization](), [Mobile](), [Claude](), [Kotlin](), [Swift](), [MCP](), [Coroutines](), [Claude Code](), [codex]() Tags: [agent](), [android](), [api](), [authorization](), [await](), [claude](), [claude-code](), [coroutines](), [ios](), [kotlin](), [maven-central](), [mcp](), [sdks](), [swift](), [updates]() ### AI overview WorkOS announces August updates including Agent Registration for scoped, short-lived credentials, Airlock for authorizing AI-agent actions, Relay for proxying third-party application requests, and native Swift and Kotlin SDKs for iOS and Android. ### Source excerpt Agent Registration, Airlock, Relay, iOS & Android SDKs, & more ## The biggest announcements from Webflow Conf 2026 DevFeed: [The biggest announcements from Webflow Conf 2026]() Original publisher: [Read original article]() Author: Webflow Team Published: 2026-09-02T00:00:00Z Content type: article Language: en Sources: [Webflow Blog]() Topics: [webflow](), [Artificial Intelligence](), [MCP](), [Model Context Protocol](), [Content Management System](), [GSAP](), [Code](), [Cloud](), [releases]() Tags: [2026](), [agentic](), [agents](), [ai](), [ai-agents](), [announcements](), [cloud](), [code](), [content](), [developers](), [development](), [gsap](), [inside-webflow](), [mcp](), [platform](), [product](), [products](), [releases](), [updates](), [webflow]() ### AI overview Webflow Conf 2026 introduced Source by Webflow, a platform connecting codebases and marketing technology stacks for visual and agentic development. Announcements included Campaigns, Assets, MCP updates, Releases, content agents in Webflow AEO, automatically generated Agent Instructions, and Agent Presence. ### Source excerpt A recap of our biggest product announcements so far, including the all-new Source, by Webflow. ## Introducing Orbit: Turn Any Task Into the Right API Calls DevFeed: [Introducing Orbit: Turn Any Task Into the Right API Calls]() Original publisher: [Read original article]() Author: Abhinav Asthana Published: 2026-08-27T16:00:00Z Content type: article Language: en Sources: [Postman Blog]() Topics: [API](), [MCP Server](), [Artificial Intelligence](), [MCP](), [Postman](), [REST API](), [Claude Code]() Tags: [agents](), [ai](), [ai-agents](), [api-discovery](), [blog](), [free](), [general](), [mcp](), [mcp-server](), [model-context-protocol](), [orbit](), [post](), [rest-api]() ### AI overview Postman introduces Orbit, a free API discovery tool for AI agents. Agents can describe a task to find suitable public API endpoints, then select an endpoint and receive an integration brief covering authentication, URLs, request steps, parameters, response codes, dependencies, and common pitfalls. Orbit is available as an MCP server and a REST API, with no account, API key, or OAuth setup required. ### Source excerpt Orbit is a free API discovery tool for AI agents. Describe a task, get the endpoints that fit, then get a task brief to integrate them. No account, no auth. The post Introducing Orbit: Turn Any Task Into the Right API Calls appeared first on Postman Blog. ## Pipes compared to Nango, Composio, Arcade, Paragon, and Merge DevFeed: [Pipes compared to Nango, Composio, Arcade, Paragon, and Merge]() Original publisher: [Read original article]() Author: WorkOS Published: 2026-08-27T00:00:00Z Content type: comparison Language: en Sources: [WorkOS Blog]() Topics: [Tool](), [API](), [MCP](), [Model Context Protocol](), [Deployment]() Tags: [api](), [comparison](), [deployment](), [integrations](), [mcp](), [pricing](), [tool]() ### AI overview A comparison of Pipes, Nango, Composio, Arcade, Paragon, and Merge, examining their positions across credential, integration-runtime, and agent-tool layers. It covers catalog units, synchronization, agent capabilities, deployment, pricing, and product-selection considerations. ### Source excerpt Six products, three layers of the same stack, and one vendor that sits in two of them. Catalog units, sync, the agent story, deployment, pricing, and when to pick each. ## Just landed in the Neon CLI DevFeed: [Just landed in the Neon CLI]() Original publisher: [Read original article]() Author: Carlota Soto Published: 2026-08-25T12:00:00Z Content type: article Language: en Sources: [Blog -- Neon Docs]() Topics: [Command-line interface](), [Databases](), [MCP](), [Agent Skills](), [API keys]() Tags: [agent-skills](), [agents](), [ci](), [cli](), [coding](), [database](), [diagnostics](), [mcp](), [product](), [tool]() ### AI overview An update on recent Neon CLI changes, including the shorter npm package name, agent-focused setup for MCP and skills, project and branch linking, environment-variable management, database diagnostics, dashboard access, and project-scoped keys. ### Source excerpt The Neon CLI moved fast over the last couple of months. It is a key tool for agents, who do all the work without ever opening the Console - let's take a look at some of recent changes. ## What Does Xirp Do? Key Features, Use Cases, and Alternatives DevFeed: [What Does Xirp Do? Key Features, Use Cases, and Alternatives]() Original publisher: [Read original article]() Author: Zohar Einy Published: 2026-08-18T14:34:23Z Content type: article Language: en Sources: [Developer Experience & Platform Engineering Blog | Port]() Topics: [AI-assisted coding](), [codex](), [Claude Code](), [macOS](), [internal developer portal](), [Backstage](), [MCP](), [sdlc](), [Command-line interface](), [Code]() Tags: [agentic](), [ai-coding-agents](), [backstage](), [claude-code](), [codex](), [coding-agents](), [gemini](), [macos](), [mcp](), [sdlc](), [software-catalog]() ### AI overview Xirp is Spotify's macOS desktop app for running Claude Code, Codex, and Gemini in parallel persistent terminal sessions. It provides isolated git worktrees, preserves session context when switching agents, and can connect to Spotify Portal so agents receive software catalog context through MCP. ### Source excerpt Xirp is Spotify's app for running AI coding agents in parallel sessions. What it does, when to use it, and the main alternatives. ## New in Confluent Intelligence and AI Tools: Making Agents Native to the Stream, Expanded Model Support, New Agent Skills, and Copilot DevFeed: [New in Confluent Intelligence and AI Tools: Making Agents Native to the Stream, Expanded Model Support, New Agent Skills, and Copilot]() Original publisher: [Read original article]() Author: Confluent Staff Published: 2026-08-18T14:00:10Z Content type: article Language: en Sources: [Confluent: Data in motion]() Topics: [Artificial Intelligence](), [apache-flink](), [Kafka](), [streaming-data-processing](), [real-time](), [MCP Server](), [Agent Skills](), [MCP](), [Inference](), [Google](), [ibm]() Tags: [ai](), [ai-ready-data](), [ai-tools](), [apache-flink](), [confluent](), [confluent-cloud](), [google](), [ibm](), [kafka](), [mcp](), [mcp-server](), [real-time](), [skills](), [streaming-data-processing](), [support](), [tools]() ### AI overview Confluent announces updates to Confluent Intelligence and related AI tools for building production AI systems on Apache Kafka and Apache Flink. The release adds expanded time-series model support, a generally available Real-Time Context Engine, updates to the fully managed MCP Server, Agent Skills for AI coding assistants, and Confluent Copilot. The features are intended to provide agents and applications with fresh business context and governed access to live data and infrastructure. ### Source excerpt Explore new AI features and AI tools: support for IBM Granite Time Series models and TimesFM models (EA), enhanced Real-Time Context Engine experience, new Agent Skills, Confluent Copilot ## WorkOS Applied AI Showcase July 28 2026 - Moving to an AI-native Organization DevFeed: [WorkOS Applied AI Showcase July 28 2026 - Moving to an AI-native Organization]() Original publisher: [Read original article]() Author: WorkOS Published: 2026-08-14T13:36:57Z Content type: article Language: en Sources: [WorkOS Blog]() Topics: [Artificial Intelligence](), [Low-Code / Internal Tools](), [AI-assisted coding](), [Containers](), [MCP](), [Command-line interface](), [incident](), [Security](), [datadog](), [Pull Request](), [Slack](), [GitHub]() Tags: [agent](), [agents](), [ai](), [applied-ai](), [cli](), [coding](), [coding-agents](), [containers](), [datadog](), [demo](), [event](), [github](), [incident](), [internal-tools](), [mcp](), [organization](), [pull-request](), [slack](), [talks](), [team]() ### AI overview WorkOS's Applied AI Showcase in New York presented five internal tools--Horizon, Blog Bot, the CLI, Wallaby, and Atlas--through live demos and talks. The article explains how the Applied AI team helps non-engineering functions build AI-powered workflows and systems. ### Source excerpt WorkOS is becoming an AI-native organization. The Applied AI Showcase in NYC on July 28th 2026 showed exactly how with live demos and talks from the Applied AI team. ## One audit trail for every coding agent, and what it proves DevFeed: [One audit trail for every coding agent, and what it proves]() Original publisher: [Read original article]() Author: WorkOS Published: 2026-08-13T00:00:00Z Content type: article Language: en Sources: [WorkOS Blog]() Topics: [audit trail](), [audit](), [coding](), [Claude Code](), [codex](), [OpenClaw](), [SIEM, Security, Observability](), [MCP]() Tags: [agent](), [agents](), [api](), [audit](), [audit-trail](), [claude](), [claude-code](), [code](), [codex](), [coding](), [logging](), [mcp](), [siem](), [streaming](), [visibility]() ### AI overview This article describes WorkOS audit logging for Claude Code, Codex, OpenClaw, and pi. Its shared plugin and harness capture agent session, prompt, and tool lifecycle events, resolve activity to people, and make events queryable through a console, Export API, SIEM streaming, and MCP. ### Source excerpt We built audit logging for Claude Code, Codex, OpenClaw and pi with no API key on any laptop. Use it to get total visibility into your entire org's agentic activity. ## Introducing the Port plugin for coding agents DevFeed: [Introducing the Port plugin for coding agents]() Original publisher: [Read original article]() Author: Matan Grady Published: 2026-08-11T17:29:31Z Content type: article Language: en Sources: [Developer Experience & Platform Engineering Blog | Port]() Topics: [AI-assisted coding](), [MCP](), [MCP Server](), [Claude Code](), [cursor](), [codex](), [pull-requests](), [Kubernetes]() Tags: [agents](), [automation](), [claude-code](), [codex](), [coding-agents](), [copilot](), [cursor](), [deployment](), [kubernetes](), [mcp](), [mcp-server](), [pull-requests]() ### AI overview Port introduces a plugin for coding agents that packages Port Skills and connects an up-to-date Port MCP server. The plugin gives Claude Code, Cursor, Codex, Copilot, and other coding agents guidance for using Port, reducing repeated tool experimentation and context usage while applying Port's best practices. Examples include building Kubernetes pod self-healing workflows, extending blueprints with deployment-frequency data, and creating ticket-resolution flows that turn Jira tickets into pull requests. ### Source excerpt Give your coding agent the context to work with Port: install the official Port plugin. ## Deploy MCP Servers on AWS Lambda with Serverless Framework v4 DevFeed: [Deploy MCP Servers on AWS Lambda with Serverless Framework v4]() Original publisher: [Read original article]() Author: Serverless Team Published: 2026-08-11T00:00:00Z Content type: tutorial Language: en Sources: [Serverless Blog]() Topics: [MCP](), [AWS Lambda](), [serverless framework](), [Streaming]() Tags: [aws](), [aws-lambda](), [cloud-computing](), [faas](), [function-as-a-service](), [infrastructure-as-code](), [mcp](), [news](), [pricing](), [serverless](), [serverless-architecture](), [serverless-framework](), [streaming](), [yaml]() ### AI overview A Serverless Framework v4.41.0 deployment workflow for MCP servers on AWS Lambda, using YAML and providing an HTTPS endpoint, response streaming, and pay-per-request pricing. ### Source excerpt Serverless Framework v4.41.0 deploys MCP servers to AWS Lambda in a few lines of YAML - a real HTTPS endpoint, response streaming, and pay-per-request pricing. ## Why every engineering org needs an agentic registry DevFeed: [Why every engineering org needs an agentic registry]() Original publisher: [Read original article]() Author: Matar Peles Published: 2026-08-10T11:43:10Z Content type: article Language: en Sources: [Developer Experience & Platform Engineering Blog | Port]() Topics: [Agent Skill](), [MCP](), [cursor](), [Azure](), [bedrock](), [site-reliability-engineering]() Tags: [agent-skill](), [agentic](), [agents](), [azure](), [bedrock](), [coding](), [governance](), [mcp](), [slack](), [workflows]() ### AI overview The article argues that engineering organizations need an agentic registry to manage the rapid growth of agents and skills. It describes registries for SKILL.md files, deployed agents, and approved MCP servers, with capabilities for discovery, standardization, governance, and workflow composition. ### Source excerpt Why every engineering org needs an agentic registry ## Context Engineering for AI Agents: What Actually Works at Scale DevFeed: [Context Engineering for AI Agents: What Actually Works at Scale]() Original publisher: [Read original article]() Author: Gur Shafriri Published: 2026-08-10T11:31:32Z Content type: article Language: en Sources: [Developer Experience & Platform Engineering Blog | Port]() Topics: [Artificial Intelligence](), [MCP](), [Retrieval Augmented Generation (RAG)](), [data](), [Large Language Model]() Tags: [agents](), [ai](), [ai-agents](), [architecture](), [cost](), [data](), [mcp](), [rag](), [tokens]() ### AI overview The article argues that AI agents perform poorly when their context is fragmented across tools such as GitHub, Jira, and PagerDuty. It presents a unified relational context layer as a way to improve accuracy, reduce token consumption, and speed up decisions. It contrasts this approach with MCP, which provides tool access but not an architecture for relationships, and RAG, which retrieves by vector similarity without reliably representing connections. ### Source excerpt Context engineering for AI agents: why MCP and RAG fall short, and how a relational context lake cuts tokens and raises accuracy. ## Introducing Mintlify Index DevFeed: [Introducing Mintlify Index]() Original publisher: [Read original article]() Author: Kyan Yang Published: 2026-08-06T00:00:00Z Content type: release Language: en Sources: [Mintlify Blog]() Topics: [Documentation](), [AI-assisted coding](), [API](), [MCP](), [MCP Server]() Tags: [announcements](), [api](), [beta](), [coding-agents](), [documentation](), [experiment](), [mcp](), [mcp-server](), [retrieval]() ### AI overview Mintlify introduces Mintlify Index, a retrieval layer that aggregates documentation from 9,000 Mintlify-powered sites for coding agents. It routes documentation-related queries to optimized retrieval and other queries to an external web search provider, with fallback between sources. The article reports an experiment in which Index was preferred in 96 of 150 implementation-planning tasks and completed tasks 48% faster end-to-end, with higher factual correctness and citation support and fewer critical errors. Mintlify launched Index as a free beta with an API and MCP server. ### Source excerpt Mintlify Index aggregates the docs of 9000 Mintlify-powered documentation sites into a natural language retrieval layer for coding agents. ## Import a Figma design into Webflow with one prompt DevFeed: [Import a Figma design into Webflow with one prompt]() Original publisher: [Read original article]() Author: Stefan Judis Published: 2026-08-06T00:00:00Z Content type: article Language: en Sources: [Webflow Blog]() Topics: [Figma](), [webflow](), [MCP](), [Claude](), [Artificial Intelligence](), [Tooling](), [Template]() Tags: [ai](), [anthropic](), [claude](), [design](), [development](), [figma](), [figma-plugin](), [mcp](), [tokens](), [tooling](), [webflow]() ### AI overview The article describes importing a Figma design into an empty Webflow site using Claude Desktop, two MCP connectors, and a single loose prompt. The process creates design tokens, classes, components, and uploaded assets without a dedicated Figma import tool or manual rebuilding. ### Source excerpt Use Claude connectors to import a Figma design into Webflow. Webflow MCP handles tokens, classes, components, and assets. ## What we've heard, and what comes next DevFeed: [What we've heard, and what comes next]() Original publisher: [Read original article]() Author: Ben Haefele Published: 2026-08-03T00:00:00Z Content type: article Language: en Sources: [Webflow Blog]() Topics: [Artificial Intelligence](), [webflow](), [Content Management System](), [Code](), [Authorization](), [cursor](), [MCP](), [ChatGPT](), [Claude]() Tags: [agents](), [ai](), [analytics](), [build-faster](), [building](), [chatgpt](), [claude](), [code](), [cursor](), [efficiency](), [inside-webflow](), [mcp](), [metrics](), [platform](), [testing](), [tools](), [webflow](), [workflows]() ### AI overview Webflow describes how AI-assisted site building has become fast, while ongoing work such as updating, managing, testing, optimizing, and personalizing sites remains the larger challenge for marketers. The article outlines Webflow's agent-oriented roadmap, including branch-based changes, roles and permissions, activity logging, and MCP access to Webflow Analytics. ### Source excerpt AI made building fast. It didn't change the updating, testing, and optimizing that marketers are still responsible for every day. Here's our take. ## Vercel MCP now supports the 2026-07-28 MCP specification DevFeed: [Vercel MCP now supports the 2026-07-28 MCP specification]() Original publisher: [Read original article]() Author: Josh Souphanthong Published: 2026-07-31T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [MCP](), [Model Context Protocol](), [Vercel](), [SDKs](), [Authorization](), [client](), [Server](), [changelog]() Tags: [2026](), [announcement](), [authorization](), [changelog](), [documentation](), [mcp](), [sdk](), [server](), [vercel]() ### AI overview Vercel MCP supports the 2026-07-28 MCP specification, adding a stateless request model and updated authorization behavior. Existing 2025-protocol clients continue to work, while compatible newer clients adopt the specification automatically through the same endpoint and connection. ### Source excerpt Vercel MCP now supports the 2026-07-28 MCP specification, giving newer clients a stateless request model and updated authorization behavior without any change on the client side. Clients built for the 2025 protocol keep working exactly as before, and clients that understand the new specification pick it up automatically. Both protocol versions are served from the same endpoint through the official MCP SDK v2 and mcp-handler 2.x, which added support for the latest spec, so a single connection handles either protocol. Nothing about setup changes. Add the server the same way you always have. npx add-mcp https://mcp.vercel.com You can also run vercel mcp. See the Vercel MCP documentation to connect your client. For the full list of protocol changes, read the 2026 specification changelog and the authorization announcement. Read more [Next page]()