anymcp 0.0.4

An adapter library for Model Context Protocol (MCP) SSE servers to connect as stdio

AnyMCP

An adapter library for Model Context Protocol (MCP) SSE servers to connect as stdio.

Overview

AnyMCP provides a bridge between SSE-based (Server-Sent Events) MCP servers and standard input/output (stdio). It allows you to connect to remote model servers that implement MCP over SSE and interact with them using traditional stdio interfaces.

Features

• Connect to MCP servers via SSE endpoints
• Bridge SSE communication to standard input/output
• Maintain persistent connections with automatic reconnection
• Support for authentication via bearer tokens
• Comprehensive logging with adjustable verbosity
• Configurable timeouts and heartbeat intervals

This package is meant to be used with Arcee AnyMCP. Arcee AnyMCP makes it super easy to deploy your own MCP servers.

Installation

Using pip

pip install anymcp

From source

git clone https://github.com/arcee-ai/anymcp.git
cd anymcp
pip install -e .

Usage

Command Line Interface

Connect to an SSE-based MCP server:

anymcp connect http://localhost:8000/sse

With authentication:

anymcp connect http://localhost:8000/sse --token YOUR_AUTH_TOKEN

Add custom headers:

anymcp connect http://localhost:8000/sse --header "X-Custom-Header=Value"

Enable debug logging:

anymcp connect http://localhost:8000/sse --debug

Python API

Use AnyMCP in your Python applications:

import asyncio
from anymcp import connect_sse_as_stdio

async def main():
    async with connect_sse_as_stdio(
        sse_url="http://localhost:8000/sse",
        token="YOUR_AUTH_TOKEN",
        timeout=5.0,
        sse_read_timeout=300.0
    ) as (reader, writer):
        # Now your application can communicate with the MCP server
        # through reader and writer streams
        pass

if __name__ == "__main__":
    asyncio.run(main())

Development

Setup

# Install in development mode
pip install -e ".[dev]"

Running Tests

make test

Code Quality

# Format code
make style

# Check code quality
make quality

Building

# Build package
make pip

# Upload to PyPI
make pip-upload

Docker

# Build Docker image
make docker-buildx

# Build and push Docker image
make docker-buildx-push

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.