#103 · Primary category: LLM Application Frameworks
xmcp
The TypeScript MCP framework
Project last updated:08/29/26
GitHub Stars
1.3K
Forks
94
Contributors
34
License
MIT
Why we included this project
Hand-writing an MCP server tends to bury your actual tools under protocol boilerplate before you can expose anything to an LLM. xmcp sidesteps most of that for TypeScript developers: drop a file into a tools or prompts directory and it registers automatically, so the MCP plumbing never lives in your own code. Hot reloading keeps iteration fast, and a middleware system puts authentication and request handling into the flow instead of tacking them on later. It also initializes cleanly inside an existing Next.js or Express app and deploys to Vercel with zero configuration, which matters for teams already working in that stack. If your goal is exposing internal APIs or custom capabilities to assistants without writing protocol handlers by hand, this gets an MCP server up and shipped quickly.
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