Aider

🚀 Aider MCP Server: AI Helper for Aider

The aider-mcp-server is an MCP (Modular Conversation Protocol) server designed to interact with advanced AI models such as Claude. This project aims to simplify the integration and expansion process through a standardized interface.

✨ Features

• Modular Architecture: Designed following the "MCP Protocol" principles, with loosely coupled components for easy maintenance and upgrades.
• High-Performance Communication: Supports high-concurrency connections, ensuring stable operation in multi-user environments.
• Flexible Adaptability: With a plug-in design, it supports the integration of multiple AI service providers (e.g., Claude, GPT-4).

🚀 Quick Start

Install Dependencies

pip install aider-mcp-server

Start the Server

aider-mcp-server --editor-model openai/gpt-4o

Example Request

Request Example

{
  "name": "aider_ai_code",
  "parameters": {
    "substring": "gemini"
  }
}

Response Result

{
  "success": true,
  "diff": "+ This is a test diff line.\n- This is another test diff line."
}

📚 Documentation

Core Components

Server Layer

Handles MCP protocol communication, receiving and sending requests/responses.

Atomic Layer (Atoms)

Pure and reusable functional components:

Tools

• aider_ai_code: Provides AI programming assistance.
• list_models: Lists supported AI models.

Helper Functions

• utils.py: Contains constants and some utility tools, such as the default model name.
• data_types.py: Defines Pydantic data structures to ensure data validation.
• logging.py: Configures a unified logging format for console and file output.

Server Logic

• server.py: Initializes the MCP server, registers atomic layer tools, processes incoming requests, routes them to the corresponding tool logic according to the MCP protocol, and sends responses.

Plugin System

Allows adding custom functional modules to enhance server extensibility.

🔧 Technical Details

• Design Philosophy: Follows the "Single Responsibility" principle, with each component focusing on a specific task.
• Communication Mechanism: Uses WebSocket or HTTP protocols for real-time interaction.
• Data Processing: Performs data validation and deserialization through Pydantic.

Code Structure

.
├── ai_docs                   # AI-related documentation
│   ├── just-prompt-example-mcp-server.xml
│   └── programmable-aider-documentation.md
├── pyproject.toml            # Project metadata and dependency management
├── README.md                 # Project description file
├── specs                     # Normative files
│   └── init-aider-mcp-exp.md
├── src                       # Source code directory
│   └── aider_mcp_server      # Main server package
│       ├── __init__.py       # Package initialization
│       ├── __main__.py       # Server startup entry point
│       ├── atoms             # Core, reusable components (pure functions)
│       │   ├── __init__.py
│       │   ├── data_types.py # Pydantic data structure definition
│       │   ├── logging.py    # Custom logging configuration
│       │   ├── tools         # Specific implementation of each tool
│       │   │   ├── __init__.py
│       │   │   ├── aider_ai_code.py # AI programming assistance tool logic
│       │   │   └── aider_list_models.py # List models tool logic
│       │   └── utils.py      # Common functions and constants (e.g., default model)
│       ├── server.py         # MCP server logic, tool registration, request processing
│       └── tests             # Unit and integration tests
│           ├── __init__.py
│           └── atoms         # Test atomic layer components
│               ├── __init__.py
│               ├── test_logging.py # Test logging functionality
│               └── tools     # Test tool logic
│                   ├── __init__.py
│                   ├── test_aider_ai_code.py # AI programming assistance tool test
│                   └── test_aider_list_models.py # List models tool test

• src/aider_mcp_server: Contains the core logic and configuration of the server.
• __main__.py: Serves as the application entry point, responsible for parsing command-line arguments and starting the server.

Configuration Options

--editor-model <model_name>    # Specify the editor model to use, default is Claude-2
--listen <host>                # Set the listening address, default is localhost
--port <number>                # Set the listening port, default is 8080

Example Usage

aider-mcp-server --editor-model openai/gpt-4o --listen 127.0.0.1 --port 8090

🛠️ Development Guide

Contribute Code

1. Clone the Repository

git clone https://github.com/yourusername/aider-mcp-server.git
cd aider-mcp-server

2. Create a Feature Branch

git checkout -b feature/new-feature

3. Commit Code

git add .
git commit -m "Add new feature"
git push origin feature/new-feature

4. Submit a Pull Request Submit a Pull Request on GitHub, ensuring that the code complies with project specifications.

Report Issues

If you encounter any problems or have suggestions for improvement, please visit the GitHub repository to submit Issues.

📄 License

This project is open-sourced under the MIT License. For detailed license information, please refer to the LICENSE file.