MCP ExplorerExplorer

Aiohttp Mcp

@kulapardon a year ago
3 MIT
FreeCommunity
AI Systems
Tools for building Model Context Protocol (MCP) servers on top of aiohttp

Overview

What is Aiohttp Mcp

aiohttp-mcp is a set of tools designed for building Model Context Protocol (MCP) servers on top of the aiohttp framework, facilitating the development of asynchronous web applications that utilize the MCP.

Use cases

Use cases for aiohttp-mcp include developing real-time applications, microservices that require context management, and any web application that benefits from asynchronous processing and MCP integration.

How to use

To use aiohttp-mcp, install it via pip or the uv package manager. You can create a basic MCP server by initializing AiohttpMCP, defining tools with decorators, and building an application using build_mcp_app.

Key features

Key features include easy integration with aiohttp web applications, support for MCP tools, an async-first design, type hints support, a debug mode for development, and flexible routing options.

Where to use

aiohttp-mcp can be used in various fields that require asynchronous web applications, particularly those that implement the Model Context Protocol for managing contextual data in applications.

Content

aiohttp-mcp

GitHub Actions Workflow Status
codecov
pre-commit.ci status
PyPI - Version
PyPI Downloads
PyPI - Python Version
GitHub License

Tools for building Model Context Protocol (MCP) servers on top of aiohttp.

Features

  • Easy integration with aiohttp web applications
  • Support for Model Context Protocol (MCP) tools
  • Async-first design
  • Type hints support
  • Debug mode for development
  • Flexible routing options

Installation

With uv package manager:

uv add aiohttp-mcp

Or with pip:

pip install aiohttp-mcp

Quick Start

Basic Server Setup

Create a simple MCP server with a custom tool:

import datetime
from zoneinfo import ZoneInfo

from aiohttp import web

from aiohttp_mcp import AiohttpMCP, build_mcp_app

# Initialize MCP
mcp = AiohttpMCP()


# Define a tool
@mcp.tool()
def get_time(timezone: str) -> str:
    """Get the current time in the specified timezone."""
    tz = ZoneInfo(timezone)
    return datetime.datetime.now(tz).isoformat()


# Create and run the application
app = build_mcp_app(mcp, path="/mcp")
web.run_app(app)

Using as a Sub-Application

You can also use aiohttp-mcp as a sub-application in your existing aiohttp server:

import datetime
from zoneinfo import ZoneInfo

from aiohttp import web

from aiohttp_mcp import AiohttpMCP, setup_mcp_subapp

mcp = AiohttpMCP()


# Define a tool
@mcp.tool()
def get_time(timezone: str) -> str:
    """Get the current time in the specified timezone."""
    tz = ZoneInfo(timezone)
    return datetime.datetime.now(tz).isoformat()


# Create your main application
app = web.Application()

# Add MCP as a sub-application
setup_mcp_subapp(app, mcp, prefix="/mcp")

web.run_app(app)

Using Streamable HTTP Transport

For production deployments requiring advanced session management, you can use the streamable HTTP transport mode:

import datetime
from zoneinfo import ZoneInfo

from aiohttp import web

from aiohttp_mcp import AiohttpMCP, TransportMode, build_mcp_app

# Initialize MCP
mcp = AiohttpMCP()


# Define a tool
@mcp.tool()
def get_time(timezone: str) -> str:
    """Get the current time in the specified timezone."""
    tz = ZoneInfo(timezone)
    return datetime.datetime.now(tz).isoformat()


# Create application with streamable transport
app = build_mcp_app(mcp, path="/mcp", transport_mode=TransportMode.STREAMABLE_HTTP, stateless=True)
web.run_app(app)

Client Example

Here’s how to create a client that interacts with the MCP server:

import asyncio

from mcp import ClientSession
from mcp.client.sse import sse_client


async def main():
    # Connect to the MCP server
    async with sse_client("http://localhost:8080/mcp") as (read_stream, write_stream):
        async with ClientSession(read_stream, write_stream) as session:
            # Initialize the session
            await session.initialize()

            # List available tools
            tools = await session.list_tools()
            print("Available tools:", [tool.name for tool in tools.tools])

            # Call a tool
            result = await session.call_tool("get_time", {"timezone": "UTC"})
            print("Current time in UTC:", result.content)


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

More Examples

For more examples, check the examples directory.

Development

Setup Development Environment

  1. Clone the repository:
git clone https://github.com/kulapard/aiohttp-mcp.git
cd aiohttp-mcp
  1. Create and activate a virtual environment:
uv venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
  1. Install development dependencies:
uv sync --all-extras

Running Tests

uv run pytest

Requirements

  • Python 3.10 or higher
  • aiohttp >= 3.9.0, < 4.0.0
  • aiohttp-sse >= 2.2.0, < 3.0.0
  • anyio >= 4.9.0, < 5.0.0
  • mcp >= 1.8.0, < 2.0.0

License

This project is licensed under the MIT License - see the LICENSE file for details.

Contributing

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

Tools

No tools

Comments

Recommend MCP Servers

View All MCP Servers