MCPgee
MCPgee
MCPgeeMCPgee

Automcp

v1.0.0•Developer Tools•stable

Easily convert tool, agents and orchestrators from existing agent frameworks to MCP servers

automcpmcpai-integration
Share:
300
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Automcp?

Automcp is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to easily convert tool, agents and orchestrators from existing agent frameworks to mcp servers

Easily convert tool, agents and orchestrators from existing agent frameworks to MCP servers

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Easily convert tool, agents and orchestrators from existing

Use Cases

Convert tools and agents from existing frameworks to MCP servers.
Migrate agent implementations between different frameworks seamlessly.
Integrate orchestrators and tools as standardized MCP servers.
NapthaAI

Maintainer

LicenseApache-2.0
Languagepython
Versionv1.0.0
UpdatedApr 20, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx automcp

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Automcp

Automcp is a Python toolkit that wraps agents and orchestrators built in popular AI frameworks — CrewAI, LangGraph, LlamaIndex, OpenAI Agents SDK, Pydantic AI, and mcp-agent — and exposes them as standard MCP servers. Instead of rewriting agent logic to fit the MCP protocol, you point Automcp at your existing agent class and it generates the server scaffolding automatically. The resulting server can be run locally over STDIO or deployed via SSE, making your agents accessible from any MCP client including Claude Desktop and Cursor.

Prerequisites

  • Python 3.10+ and either pip or uv installed
  • An existing agent built with CrewAI, LangGraph, LlamaIndex, OpenAI Agents SDK, Pydantic AI, or mcp-agent
  • API keys required by your agent framework (e.g., OPENAI_API_KEY, SERPER_API_KEY)
  • Claude Desktop or another MCP client to consume the resulting server
1

Install the naptha-automcp package

Install Automcp via pip or add it to your project with uv. The package name on PyPI is naptha-automcp.

pip install naptha-automcp
# or with uv:
uv add naptha-automcp
2

Initialize a server scaffold for your framework

Run automcp init with the -f flag to specify your agent framework. This generates a run_mcp.py file pre-configured for the chosen framework.

# Replace <framework> with: crewai, langgraph, llamaindex, openai, pydantic, or mcp_agent
automcp init -f crewai
3

Edit run_mcp.py to import your agent

Open the generated run_mcp.py and import your agent class, define the input schema with required parameters, and pass the agent instance to the appropriate adapter (e.g., create_crewai_adapter).

from crew import MarketingPostsCrew
from naptha_automcp.adapters import create_crewai_adapter

mcp_server = create_crewai_adapter(
    orchestrator_instance=MarketingPostsCrew().crew(),
    name="marketing_posts_crew",
    description="Creates social media marketing posts",
    input_schema=InputSchema
)
4

Set required environment variables

Export the API keys your agent needs before starting the server. These depend on your framework and the tools your agent uses.

export OPENAI_API_KEY=sk-...
export SERPER_API_KEY=your-serper-key
5

Serve the MCP server

Launch your agent as an MCP server. Use STDIO transport for local Claude Desktop integration or SSE for network-accessible deployments.

automcp serve -t stdio
# or for SSE:
automcp serve -t sse

Automcp Examples

Client configuration

Add this to claude_desktop_config.json to connect Claude Desktop to your automcp-wrapped agent running over STDIO.

{
  "mcpServers": {
    "my-agent": {
      "command": "python",
      "args": ["run_mcp.py"],
      "env": {
        "OPENAI_API_KEY": "sk-..."
      }
    }
  }
}

Prompts to try

Once your agent is running as an MCP server, use these prompts in Claude to exercise it.

- "Use the marketing_posts_crew tool to create a LinkedIn post about our new product launch"
- "Run my research agent to gather the latest information on renewable energy trends"
- "Invoke the data analysis agent with this CSV data and summarize the key findings"

Troubleshooting Automcp

automcp init generates an empty or broken run_mcp.py

Ensure you are in your project's virtual environment and that naptha-automcp is installed. The -f flag must exactly match one of: crewai, langgraph, llamaindex, openai, pydantic, mcp_agent.

Agent fails to start with ImportError when running automcp serve

The agent's dependencies must be installed in the same environment as naptha-automcp. Run 'pip install -r requirements.txt' for your agent project before serving.

Claude Desktop shows the server as disconnected

STDIO mode requires the command to stay running and read from stdin. Verify run_mcp.py does not exit immediately. Check Claude Desktop logs at ~/Library/Logs/Claude/mcp*.log for startup errors.

Frequently Asked Questions about Automcp

What is Automcp?

Automcp is a Model Context Protocol (MCP) server that easily convert tool, agents and orchestrators from existing agent frameworks to mcp servers It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Automcp?

Follow the installation instructions on the Automcp GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Automcp?

Automcp works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Automcp free to use?

Yes, Automcp is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Automcp Alternatives — Similar Developer Tools Servers

Looking for alternatives to Automcp? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.

Ecc

★ 188.2k

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Javaguide

★ 155.8k

Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发

Gemini CLI

★ 104.5k

A secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in

Awesome MCP Servers

★ 87.3k

⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.

MCP Servers

★ 86.0k

Model Context Protocol Servers

CC Switch

★ 77.5k

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Developer ToolsBrowse All Servers

Quick Config Preview

{ "mcpServers": { "automcp": { "command": "npx", "args": ["-y", "automcp"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Automcp?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides