Visit automcpEasily convert tool, agents and orchestrators from existing agent frameworks to MCP servers
About automcp
automcp converts tools, agents and orchestrators built in existing agent frameworks into MCP servers. The README lists CrewAI, LangGraph, LlamaIndex, OpenAI Agents SDK, Pydantic AI and mcp-agent as supported. An init command generates a server file that you edit to connect your agent and input schema, and a serve command runs it over stdio or SSE. Clients such as Cursor and Claude Desktop can then use the result.
It is a Python project installed from PyPI or from source, and the README mentions the uv tool. Your own agent may need model or tool API keys. The README also describes deploying to Naptha's hosted MCP platform, which needs a GitHub account. An adapter pattern allows more frameworks to be added. The README states an Apache-2.0 licence and the repository belongs to the NapthaAI organisation. It does not say whether it is affiliated with the frameworks it supports. Details come from the project's README.
Key features
- Convert agent frameworks to MCP
- Six supported frameworks
- stdio and SSE transports
- Hosted deployment option
- Adapter pattern for new frameworks
More other MCP servers
- Other

Mcp Proxy
sparfenyuk
A bridge between Streamable HTTP and stdio MCP transports
2.8K GitHub starsPythonMIT - Other

Mcp Remote
punkpeye
Connect an MCP Client that only supports local (stdio) servers to a Remote MCP Server.
1.7K GitHub starsTypeScriptMIT - Other

Kanzo
emanuele-em
Self-hosted, sharable kanban for humans and agents. One 4.5 MB binary, 4.5 MB of RAM, 10 to 60 tokens per agent reply, starts in 2 ms, zero setup.
1.2K GitHub starsRustAGPL-3.0 - Other

čå PPT.skill
zhouwei713
įæåįūååŊįžčūåį PPT į Agent Skill
484 GitHub starsPythonMIT - Other

mcptoon
activeing123
MCP tool discovery burns 71,929 tokens. mcptoon drops it to 581 (â99.2%, measured). Zero dependencies.
431 GitHub starsPythonApache-2.0