Model Context Protocol servers

What is Model Context Protocol servers?

A collection of reference implementations for the Model Context Protocol (MCP), along with references to community-built servers. It demonstrates how MCP gives Large Language Models (LLMs) secure, controlled access to tools and data sources.

How to use Model Context Protocol servers?

Each reference server is implemented with either the TypeScript or Python MCP SDK. Consult the server’s directory for specific usage instructions.

Key features of Model Context Protocol servers

• Collection of reference MCP server implementations in TypeScript and Python.
• Demonstrates secure, controlled tool and data access for LLMs.
• Includes official integrations from companies like Browserbase, Cloudflare, Neo4j, and more.
• Features a growing set of community-developed servers across various domains.
• Lists are maintained in alphabetical order to minimize merge conflicts.

Use cases of Model Context Protocol servers

• Secure file operations with configurable access controls (Filesystem server).
• Read-only database access with schema inspection (PostgreSQL server).
• Web content fetching and conversion for efficient LLM usage (Fetch server).
• Knowledge graph-based persistent memory for conversational context (Memory server).
• Browser automation and web scraping (Puppeteer server).

FAQ from Model Context Protocol servers

How are the reference servers implemented?

They are implemented with either the TypeScript MCP SDK or Python MCP SDK.

What are official integrations?

Official integrations are maintained by companies building production ready MCP servers for their platforms.

Are community servers endorsed by Anthropic?

No, community servers are untested and should be used at your own risk. They are not affiliated with or endorsed by Anthropic.

Why are lists sorted alphabetically?

Lists in this README are maintained in alphabetical order to minimize merge conflicts when adding new items.