A protocol for seamless integration between LLM applications and external data sources

Documentation | Specification | Discussions

The Model Context Protocol (MCP) is an open protocol that enables seamless integration between LLM applications and external data sources and tools. Whether you're building an AI-powered IDE, enhancing a chat interface, or creating custom AI workflows, MCP provides a standardized way to connect LLMs with the context they need.

• 📚 Read the Documentation for guides and tutorials
• 🔍 Review the Specification for protocol details
• 💻 Use our SDKs to start building:
  • TypeScript SDK
  • Python SDK
  • Java SDK
  • Kotlin SDK
  • C# SDK
  • Go SDK
  • PHP SDK
  • Ruby SDK
  • Rust SDK
  • Swift SDK

• modelcontextprotocol - User documentation and protocol specification
• typescript-sdk - TypeScript implementation
• python-sdk - Python implementation
• java-sdk - Java implementation
• kotlin-sdk - Kotlin implementation
• csharp-sdk - C# implementation
• go-sdk - Go implementation
• php-sdk - PHP implementation
• ruby-sdk - Ruby implementation
• rust-sdk - Rust implementation
• swift-sdk - Swift implementation
• create-kotlin-server - Kotlin sample server
• servers - List of maintained servers
• ext-auth - List of authorization extensions

We welcome contributions of all kinds! Whether you want to fix bugs, improve documentation, or propose new features, please see our contributing guide to get started.

Have questions? Join the discussion in our community forum.

The Model Context Protocol is an open source project hosted by The Linux Foundation and open to contributions from the entire community.