Model Context Protocol Servers
Official reference servers for the Model Context Protocol, connecting LLMs to tools and data.
About
Reference implementations for the Model Context Protocol fill this repository, maintained as the canonical starting point for connecting language models to external tools and data. Seven actively maintained servers cover the fundamentals: Everything, Fetch, Filesystem, Git, Memory, Sequential Thinking, and Time, while thirteen earlier examples such as GitHub, PostgreSQL, Slack, and Puppeteer now live in an archived companion repository. TypeScript servers launch with a single npx command and Python servers with uvx or pip, so any MCP client, including Claude Desktop, Cursor, or VS Code, can attach them through one JSON configuration entry. The repo also indexes official SDKs in ten languages, from TypeScript and Python to Rust, Go, and Kotlin, and links the community registry at registry.modelcontextprotocol.io that catalogs thousands of third-party servers. The code is transitioning from MIT to Apache-2.0 licensing and is positioned as educational rather than production infrastructure, but with Anthropic, OpenAI, and Google all adopting MCP, these servers function as the protocol's working textbook.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- AI Frameworks & Libraries
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Easy (2/5)
- License
- Apache-2.0
- Added
- Jul 29, 2026
Related Tools
Unified system for large-scale distributed training and inference.
Guidance language for controlling LLM generation with constraints, grammars, and JSON schemas.
Library for easily accessing and processing ML datasets.
JAX neural network library with PyTorch-like module system.
High-level deep learning API supporting JAX, TensorFlow, and PyTorch backends.
Gradient boosting library by Yandex with native categorical feature handling.