Model Context Protocol (MCP)
Open protocol that standardizes how AI applications connect to external tools, data sources and prompts via MCP servers.
Tags
Description
The Model Context Protocol (MCP) is an open standard, introduced by Anthropic in November 2024, for connecting LLM applications (hosts/clients) to external capabilities exposed by MCP servers: tools, resources and prompts. It uses JSON-RPC 2.0 over stdio or Streamable HTTP transports, and has official SDKs in many languages. The project is transitioning from the MIT License to Apache-2.0 (new code and spec contributions are Apache-2.0; docs are CC-BY-4.0).
Agent access
Related
- MCP Server Cards: MCP extension (SEP-2127, Final) defining a static JSON card that describes a remote MCP server's identity and transport endpoints so clients can find and connect to it.
Guides & comparisons
- Confine a coding agent's filesystem MCP access (Guide): Separate the workspace a coding agent sees from the files its MCP server can touch. A practical review of allowed directories, legacy Roots, read-only tools, symlinks and hard links, with a disposable acceptance checklist.
- Publish an MCP server so agents can find it (Guide): Build a small MCP server with FastMCP, test it with the MCP Inspector CLI, publish its metadata to the official MCP Registry with mcp-publisher, then get it into GitHub's registry, Glama, the Docker MCP Catalog and Index Agentica.
- Drive a headless Godot editor over MCP (Guide): Run a Godot 4.7 editor with no display on a Linux box or CI runner and let a coding agent edit scenes and scripts through Beckett, Godot Editor MCP or Godot AI. Includes tested commands, a stdlib Python probe, and the security checks we ran.
- Give your coding agent up-to-date library docs over MCP (Context7, GitMCP, DeepWiki, Microsoft Learn) (Guide): Stop your coding agent from guessing at APIs that changed after its training cutoff. Connect free remote docs MCP servers (Context7, GitMCP, DeepWiki, Microsoft Learn) to Claude Code, Codex or Cursor, learn which tool to call for what, and keep a self-hosted fallback for private docs.
- Bridge stdio and remote MCP servers: mcp-remote, Supergateway, mcp-proxy and mcpo (Guide): Put a local stdio MCP server on HTTP so remote agents can reach it, or plug a remote server into a client that only speaks stdio. Covers mcp-remote, Supergateway, mcp-proxy and mcpo: which direction each one bridges, exact commands, how to lock the endpoint down, and two dependency breakages we hit.
- Use the Index Agentica MCP server: the five real tools, their schemas and the mistakes to avoid (Guide): A reference for the five tools that mcp.indexagentica.com actually exposes (search, get_entry, get_content, list_categories and request_listing), with input schemas, live example calls and responses, the matching REST endpoints, and the wrong tool names and arguments that clients send most often.
- Add OAuth authorization to your own MCP server (Guide): A server-side walkthrough of the MCP 2026-07-28 authorization spec: publish RFC 9728 protected resource metadata, answer 401 and 403 challenges, verify JWT audience per RFC 8707, enforce per-tool scopes, and never pass tokens through. Tested with the MCP TypeScript SDK v2.
- Test your MCP server with in-process tests and Inspector CI checks (Guide): Automated tests for a TypeScript MCP server: call tools in-process through the SDK's handler.fetch, assert on structuredContent and isError, snapshot the tool list so schema changes fail review, test the bearer-token gate, spawn the stdio build, and add MCP Inspector CLI checks to CI.
- Convert documents to Markdown for agents with MarkItDown and Docling (Guide): Turn PDFs, Office files and other documents into Markdown or chunks an agent can read, with Microsoft's MarkItDown for speed and Docling for layout and tables, then expose either one to an agent over MCP.
- Agent auth and delegated access, step by step (Guide): How an agent acts for a user without holding their passwords: CIMD client registration, the MCP 2026-07-28 OAuth flow with resource indicators and audience checks, no token passthrough, vaulted third-party tokens, CIBA approvals and Cross App Access (ID-JAG).
- Add MCP servers to Claude Code (Guide): Connect Claude Code to remote and local MCP servers from the command line, choose the right scope, keep tokens out of shared config, and check that each server connected, using GitHub and Playwright as examples.
- Connect an agent to a remote MCP server (Guide): How remote MCP works over Streamable HTTP in the 2026-07-28 spec, how OAuth sign-in is discovered, and copy-paste configs for Claude Code, Codex, Cursor, Gemini CLI, VS Code and Claude connectors.
- Pay for an API as an agent with x402 (Guide): How an agent pays per request for an HTTP API or MCP tool with x402 v2, from reading the 402 response to signing a USDC payment with spend caps, on testnet first.
- Runtime guardrails for agents: Guardrails AI, NeMo Guardrails, Invariant and HOL Guard (Comparison): Four open-source guardrail layers compared: where each one sits, what a rule looks like, whether it can check tool calls, which checks need a model, what leaves your machine and how actively each is maintained. All four were installed and run on 2026-11-01.
- Game engine agent tooling compared: Unreal, Unity, Godot, Roblox and Bevy (Comparison): How a coding agent reaches into Unreal Engine, Unity, Godot, Roblox Studio and Bevy: the official MCP servers and CLIs, the main community servers, what each one runs on, how it is secured, how many tools it exposes and which ones are deprecated or inactive.
- MCP server frameworks compared: FastMCP vs mcp-use vs the official Python and TypeScript SDKs (Comparison): Four ways to build an MCP server in 2026: the official Python SDK (v2) and TypeScript SDK (v2), Prefect's FastMCP and Manufact's mcp-use. Covers languages, schemas, transports, auth, MCP Apps (UI), local testing, deployment and license.
- Work-management MCP servers compared: Asana vs monday.com vs Linear vs Notion vs Atlassian (Comparison): The official hosted MCP servers for five work-management tools (Asana, monday.com, Linear, Notion and Atlassian's Jira/Confluence server), compared on endpoint, auth, read-only options, tool exposure, admin controls and what you can self-host.
- LLM gateways compared: OpenRouter vs Vercel AI Gateway vs Cloudflare AI Gateway vs Portkey vs LiteLLM (Comparison): Five ways to put one endpoint between your agents and many model providers: two hosted model marketplaces (OpenRouter, Vercel AI Gateway), Cloudflare's proxy, and two open-source gateways you can self-host (Portkey, LiteLLM). Covers API, fallback, caching, spend controls, MCP, pricing and license.
- LiveKit Agents vs Pipecat vs OpenAI Realtime vs ElevenAgents vs Vapi: building voice agents (Comparison): Five ways to give an agent a voice compared: two open-source realtime frameworks (LiveKit Agents, Pipecat), a speech-to-speech model API (OpenAI Realtime) and two hosted voice-agent platforms (ElevenAgents, Vapi). Covers architecture, hosting, telephony, MCP tools, testing, pricing and license.
- OpenClaw vs Hermes Agent vs Pi: open-source agents you run yourself (Comparison): Three fast-moving open-source agent runtimes compared: OpenClaw (gateway-first personal assistant), Hermes Agent (self-improving agent with memory, skills and cron) and Pi (minimal, extensible coding harness). Covers interfaces, models, memory, skills, MCP, automation, safety defaults and license.
- MCP gateways compared (Comparison): Docker MCP Gateway, Stacklok ToolHive and Arcade MCP Gateways compared on where they run, how they isolate MCP servers, how clients authenticate, tool filtering and context control, policy, audit and rate limits, and licensing.
- Open-source red-teaming tools for LLM apps and agents (Comparison): Promptfoo, DeepTeam and Giskard compared as red-teaming tools for LLM apps and agents. Covers interface, what they attack, agent and MCP coverage, multi-turn attacks, framework mappings, CI use, and where attack generation and telemetry go.
- IDE and cloud coding agents compared (Comparison): Cursor, VS Code agent mode, Google Antigravity, Devin and Kiro compared on local versus cloud execution, background tasks, pull-request workflow, model choice, MCP and skills, pricing, and enterprise and privacy controls.
- Agent identity and MCP authorization platforms (Comparison): Descope, Stytch Connected Apps, Auth0 for AI Agents, WorkOS AuthKit and Arcade compared on their role in MCP OAuth, DCR and CIMD support, delegated tokens for third-party APIs, human approval, pricing and SDKs.
- Terminal coding agents compared (Comparison): Claude Code, Codex CLI, Gemini CLI, GitHub Copilot CLI, OpenCode, Cline, goose and Aider compared on license, model access, instruction files, sandboxing, headless mode, MCP and Agent Skills support.
- Discover a site's agent interfaces (Skill): A probe-then-pick workflow for finding the best machine interface a website offers (MCP, A2A, OpenAPI, Agent Skills, llms.txt, NLWeb or WebMCP), with a read-only Python script tested against live sites on 2026-11-01.
- Index Agentica lookup (Skill): Query Index Agentica through its live MCP server (exactly five tools: search, get_entry, get_content, list_categories, request_listing), its REST mirror, or the static JSON API and llms.txt, to discover agent tools, MCP servers, APIs and long-form guides, and to propose new entries.
- Pick an MCP server (Skill): A repeatable shortlist-compare-probe workflow for selecting an MCP server from Index Agentica, with two scripts that pull candidates from the live REST API and test a remote endpoint's auth without credentials.
- Connect a remote MCP server (Skill): Configure, verify and troubleshoot a remote Streamable HTTP MCP server in the major agent clients, including OAuth discovery and protocol-version checks.
- Unreal Engine development for coding agents (Skill): Rules, commands and fixes an AI coding agent needs in an Unreal Engine 5 project, from module layout and reflection macros to headless builds, automation tests, Python editor scripting and Unreal MCP.
Sources
- https://modelcontextprotocol.io
- https://github.com/modelcontextprotocol/modelcontextprotocol
- https://github.com/modelcontextprotocol/modelcontextprotocol/blob/main/LICENSE
Machine-readable
- JSON
- Markdown
- Source file on GitHub (edit via pull request)