Happy slice of mcp pizzaMCP.pizza

aider-mcp-server

MCP.Pizza Chef: disler

The idea is to hand the actual typing of code to Aider, an open-source coding assistant, while your main assistant stays in charge of planning and review. Two things are on offer: ask Aider to change specific files from a plain-English instruction, and look up which models Aider supports. Setup means downloading the project and supplying a key for whichever model you pick. The author calls it experimental, and nothing has changed since May 2025.

Unmaintained · no code changes since May 2025; author labelled it experimental
Coding

Use This MCP server To

Refactor a function without leaving my main assistant Hand a repetitive code edit to a cheaper model Add error handling to a file I point at Check which coding models I can actually use Let one assistant plan while another writes the code

README

Aider MCP Server - Experimental

Model context protocol server for offloading AI coding work to Aider, enhancing development efficiency and flexibility.

Overview

This server allows Claude Code to offload AI coding tasks to Aider, the best open source AI coding assistant. By delegating certain coding tasks to Aider, we can reduce costs, gain control over our coding model and operate Claude Code in a more orchestrative way to review and revise code.

Setup

  1. Clone the repository:
git clone https://github.com/disler/aider-mcp-server.git
  1. Install dependencies:
uv sync
  1. Create your environment file:
cp .env.sample .env
  1. Configure your API keys in the .env file (or use the mcpServers "env" section) to have the api key needed for the model you want to use in aider:
GEMINI_API_KEY=your_gemini_api_key_here
OPENAI_API_KEY=your_openai_api_key_here
ANTHROPIC_API_KEY=your_anthropic_api_key_here
...see .env.sample for more
  1. Copy and fill out the the .mcp.json into the root of your project and update the --directory to point to this project's root directory and the --current-working-dir to point to the root of your project.
{
  "mcpServers": {
    "aider-mcp-server": {
      "type": "stdio",
      "command": "uv",
      "args": [
        "--directory",
        "<path to this project>",
        "run",
        "aider-mcp-server",
        "--editor-model",
        "gpt-4o",
        "--current-working-dir",
        "<path to your project>"
      ],
      "env": {
        "GEMINI_API_KEY": "<your gemini api key>",
        "OPENAI_API_KEY": "<your openai api key>",
        "ANTHROPIC_API_KEY": "<your anthropic api key>",
        ...see .env.sample for more
      }
    }
  }
}

aider-mcp-server FAQ

Is this project still active?
No. The last code change was in May 2025, and the author already labelled it experimental at the time. It still runs, but expect no fixes, and no replacement project is named.
Which apps does it work in?
It was built for Claude Code, and any app that speaks MCP can start it from a short config block. There is a one-line command for adding it to Claude Code directly.
Do I need a paid key?
Yes. Aider drives a model of your choosing, so you supply a key for Google, OpenAI, Anthropic, or another provider, and the usage is billed to you.
Can I use this to fix a bug in my code?
Yes — you describe the fix and list the files Aider may touch, and it returns a summary of exactly what it changed.
Will it edit my files without asking?
It only edits the files you explicitly mark as editable in the request. Anything you list as read-only is used for context but left alone.
Is this useful if I do not write code?
Not really. It expects a code project on your computer and file paths within it, so it suits developers far more than general users.
How hard is the setup?
Fairly involved. You download the project, install its dependencies with a command-line tool, add your model key, and point the config at both folders.