home / mcp / aider mcp server

Aider MCP Server

Runs parallel and sequential AI coding tasks via MCP using the Aider tool; reports task outcomes and performance.

Installation

Add the following to your MCP client configuration file.

Configuration

{
  "mcpServers": {
    "eiliyaabedini-aider-mcp": {
      "url": "https://mcp.example.com/mcp",
      "headers": {
        "AIDER_MODEL": "gpt-4.1-mini"
      }
    }
  }
}

You can run multiple AI coding tasks in parallel or sequentially using MCP with the MyMCP setup. It helps you compare performance, get detailed execution reports, and coordinate tasks with a standardized interface for AI models.

How to use

You interact with an MCP client to invoke parallel or sequential AI coding tasks. Start tasks that have no dependencies and combine them into a single workflow so they can run concurrently. Use the dedicated MCP tool to plan, execute, and monitor multiple coding prompts, and review the results in a consolidated report that shows success, failure, and implementation details.

To run the MCP server locally, use the provided stdio implementation that connects via the MCP client. This setup lets you launch the local server process and communicate through standard input/output.

"AiderMCP": {
  "command": "uv",
  "args": [
    "run",
    "--with",
    "mcp[cli]",
    "mcp",
    "run",
    "/Users/path/to/aider_mcp.py"
  ]
}

How to install

Follow these concrete steps to install the required tools and set up the environment for MyMCP. You will install Aider, set up the MCP environment, and verify the setup with tests.

# Prerequisites
python3 --version
git --version

# Ensure Python 3.8+ is installed
# Install Aider (choose one method)

# Option 1: One-line installer (Mac & Linux)
curl -s https://aider.chat/install.sh | sh

# Option 1 (alternative): wget
wget -qO- https://aider.chat/install.sh | sh

# Option 2: Using pip
python -m pip install aider-install
aider-install

# Install project dependencies
pip install -e .

# Or install from requirements
pip install -r requirements.txt

# Configure environment
cp .env.sample .env

# Verify installation by running tests
python tests/test_multiple_ai.py

Configuration and running an MCP client

The MCP client communicates with the local server using a standard command setup. The following example shows how to run the local MCP server from a client, enabling parallel task execution and integration with the Aider tool.

"AiderMCP": {
  "command": "uv",
  "args": [
    "run",
    "--with",
    "mcp[cli]",
    "mcp",
    "run",
    "/Users/path/to/aider_mcp.py"
  ]
}

Available tools

code_with_multiple_ai

Tool to execute multiple AI coding prompts in parallel under MCP coordination, enabling concurrent task execution and consolidated reporting.

code_with_ai

Tool for single AI coding prompt execution within the MCP framework, used when tasks must be serialized or require isolated context.