MCP Servers
The open registry for Model Context Protocol servers. Find the right tools, resources, and prompts for your AI agents — filtered by category, transport, or use case.
Servers
206
Tools
545
Categories
11
Contributors
182
Official Anthropic MCP server providing direct access to Claude models through the Model Context Protocol. Enables AI agents to invoke Claude for sub-tasks like summarization, analysis, and code generation within agentic workflows. Supports system prompts, multi-turn conversations, and token counting. Updated for the MCP 2026-07-28 spec: a stateless request/response core that runs on serverless and edge infrastructure, a versioned extensions framework covering MCP Apps (interactive in-conversation UI) and Tasks (long-running work), and authorization hardened to align with production OAuth 2.0 and OIDC identity providers such as Entra and Okta.
Provides a structured sequential thinking tool through the Model Context Protocol. Enables AI agents to break down complex problems into numbered thought steps, revise previous thoughts, branch into alternative paths, and adjust the total number of steps dynamically. Useful for multi-step reasoning, planning, and analysis tasks that benefit from explicit step-by-step thinking.
Skills vs MCP servers
what’s the difference?Skillsthe “what to do”
A skill packages know-how — instructions, an example prompt, and recommended models — so an agent performs a task consistently. Skills add knowledge, not new connections.
MCP serversthe “how to connect”
An MCP server gives an agent new capabilities by connecting it to real systems (databases, APIs, files) over a transport. MCP adds connections and actions, not task instructions.
Rule of thumb: reach for a skill when you need the model to do a task well, and an MCP server when you need it to reach a tool or system. They compose — a skill can rely on tools an MCP server provides.
Built an MCP server?
Submit it to the registry — it’s open source and community-maintained.