Agentrix MCP: Aider in Docker

Agentrix MCP lets you run isolated Aider coding agents in Docker containers. Trigger automated code changes on a Git branch via a simple HTTP call.

How It Works

1. Send a request to the MCP server with a repo URL, branch, and Aider instructions.
2. MCP launches a Docker container (agentrix-aider image) with your parameters.
3. Inside the container:
   • The repo is cloned and the branch checked out/created.
   • Git is configured (optionally with a GitHub token).
   • Aider runs with your instructions and commits changes.
4. Container exits after processing.

Prerequisites

• Docker (install guide)
• Python 3.6+
• pip or uv (recommended for fast Python dependency management)

Quick Start

1. Clone this repo and enter the directory:

   git clone <this-repo-url>
   cd agentrix-mcp-python
   

2. Install Python dependencies:

   Using pip:

   pip install uvicorn fastapi python-dotenv docker
   

   Or, using uv (much faster):

   • Install uv (macOS/Linux):

     curl -LsSf https://astral.sh/uv/install.sh | sh
     

   • Or with pip:

     pip install uv
     

   • Then install dependencies:

     uv pip install uvicorn fastapi python-dotenv docker
     

3. Build the Docker image:

   docker build -t agentrix-aider:latest .
   

4. Set your OpenAI API key (if needed):

   export OPENAI_API_KEY='sk-YOUR_OPENAI_API_KEY'
   

   Or create a .env file with:

   OPENAI_API_KEY=sk-YOUR_OPENAI_API_KEY
   

5. Start the MCP server:

   uvicorn agentrix_mcp:app --reload --port 8000
   

   The server will be available at http://localhost:8000.

---

Tip: Use --reload for auto-reloading during development.

Now you're ready to send requests to Agentrix MCP!

---

Learn more about uv:
https://github.com/astral-sh/uv