#133 · Primary category: LLM Application Frameworks
mcp-framework
The Typescript MCP Framework
Project last updated:04/16/26
GitHub Stars
928
Forks
112
Contributors
17
License
MIT
Why we included this project
If you build tools that expose data or actions to Claude, ChatGPT, or other MCP-capable assistants, this framework removes a lot of the plumbing you would otherwise write by hand. It wraps the official MCP SDK in TypeScript-friendly base classes for tools, resources, and prompts, and it handles server setup through a CLI that scaffolds a project and adds new tools in one command. Discovery is automatic: drop a file in the right directory and the server picks it up, which keeps growing server codebases tidy without manual registration. You also get a choice of transports (stdio, SSE, HTTP streaming) and built-in auth for web endpoints, so the same codebase can go from a local CLI tool to a hosted service. Teams that already live in TypeScript and want a structured, typed foundation for their MCP servers will find this a practical starting point rather than a thin wrapper.
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