#72 · Primary category： LLM Application Frameworks
fastmcp
A TypeScript framework for building MCP servers.
Project last updated：08/29/26
GitHub Stars
3.3K
Forks
305
Contributors
86
License
MIT
Why we included this project
FastMCP is a TypeScript framework for turning your own code into an MCP server, so Claude, Copilot, or a custom agent can call your internal tools and APIs. It builds on the official SDK and handles the parts you would otherwise wire yourself, like session tracking, transports, authentication, and streaming. It also supports custom HTTP routes, edge runtimes, and an in-memory transport for unit testing without binding a port. One thing to check before adopting it: FastMCP targets the legacy handshake-based protocol revisions, not the stateless 2026 spec, so teams starting fresh on that spec should look at ViteMCP instead.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
langchain
The agent engineering platform.
dify
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
litellm
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
llama_index
LlamaIndex is the leading document agent and OCR platform