automcp
by NapthaAI
automcp allows you to easily convert tools, agents and orchestrators from existing agent frameworks into MCP servers, that can then be accessed by standardized interfaces via clients like Cursor and Claude Desktop. It supports deployment of agents, tools, and orchestrators as MCP servers for various agent frameworks.
Last updated: N/A
What is automcp?
automcp is a tool that converts agents, tools, and orchestrators from existing agent frameworks (like CrewAI, LangGraph, Llama Index, OpenAI Agents SDK, Pydantic AI, and mcp-agent) into MCP (Model Context Protocol) servers. These servers can then be accessed by standardized interfaces via clients like Cursor and Claude Desktop, enabling seamless integration with various development environments.
How to use automcp?
First, install automcp using pip or uv. Then, navigate to your project directory and use the automcp init -f <framework> command to generate the necessary server files. Edit the generated run_mcp.py file to configure your agent, including importing your agent classes and defining the input schema. Finally, install dependencies and run your MCP server using automcp serve -t sse or automcp serve -t stdio.
Key features of automcp
Converts agent frameworks to MCP servers
Supports multiple agent frameworks (CrewAI, LangGraph, Llama Index, OpenAI Agents SDK, Pydantic AI, mcp-agent)
Generates server files via CLI
Provides STDIO and SSE transport options
Supports deployment to Naptha's MCPaaS platform
Use cases of automcp
Integrating existing agent frameworks with Cursor IDE
Connecting agents to Claude Desktop
Standardizing access to agents via MCP
Deploying agents as a service on Naptha's MCPaaS platform
FAQ from automcp
What is MCP?
What is MCP?
MCP stands for Model Context Protocol. It's a standard for interacting with agents and tools.
Which agent frameworks are supported?
Which agent frameworks are supported?
Currently, automcp supports CrewAI, LangGraph, Llama Index, OpenAI Agents SDK, Pydantic AI, and mcp-agent.
How do I install automcp?
How do I install automcp?
You can install it from PyPI using pip install naptha-automcp or uv add naptha-automcp. Alternatively, you can install from source.
What is the purpose of the run_mcp.py file?
What is the purpose of the run_mcp.py file?
This file sets up and runs your MCP server. It contains server initialization code, transport handlers, and a placeholder for your agent implementation. You need to edit this file to import and configure your agent.
What are the different transport modes?
What are the different transport modes?
automcp supports STDIO and SSE transport modes. STDIO is typically used with clients like Cursor, while SSE requires you to manually start the server and configure the client to connect to it.