modelcontextprotocol/servers

Model Context Protocol Servers

What it solves

This repository provides reference implementations of servers that allow Large Language Models (LLMs) to securely and controlledly access tools and data sources through the Model Context Protocol (MCP).

How it works

These servers act as bridges between LLMs and specific data sources or tools. They are built using official MCP SDKs (available in multiple languages like TypeScript, Python, Go, and Rust) and can be configured into an MCP client (such as Claude Desktop) to extend the model's capabilities.

Who it’s for

Developers who want to build their own MCP servers or understand how to implement MCP features and SDK usage through educational examples.

Highlights

  • Diverse Reference Servers: Includes implementations for filesystem access, Git repository manipulation, a knowledge graph-based persistent memory system, and web content fetching.
  • Multi-language SDK Support: Demonstrates usage of across a wide range of SDKs including C#, Go, Java, Kotlin, PHP, Python, Ruby, Rust, Swift, and TypeScript.
  • Easy Deployment: TypeScript servers can be run directly via npx and Python servers via uvx or pip.
  • Extensible Architecture: Designed to showcase how LLMs can be given secure, controlled access to external tools and data.

Related

  • Project
  • Project
  • Project
  • Project
  • Project