Codesavant Coding Assistant

🚀 MCP-CodeSavant

MCP-CodeSavant is an under - development project that serves as a server based on the Model Context Protocol (MCP). It offers code operation, execution, and version control capabilities, enabling AI assistants to read, write, and execute code while maintaining a history of code changes.

✨ Features

• Read and write code files, with support for specific line - by - line operations.
• Execute code in multiple programming languages (Python, Node.js).
• Execute shell commands in a controlled environment.
• Track and manage code changes through version control.
• Search for content within code files.
• Restore code to a previous version.

📦 Installation

1. Clone the repository:

git clone https://github.com/twolven/mcp-codesavant.git
cd mcp-codesavant

2. Install the required dependencies:

pip install -r requirements.txt

3. Add the server configuration to your Claude desktop config.json file:

{
  "mcpServers": {
    "codesavant": {
      "command": "python",
      "args": ["path/to/codesavant.py"]
    }
  }
}

📁 Directory Structure

The server creates and manages the following directory structure:

workspaces/
├── project1/
│   ├── .code_history.json
│   └── [code files]
├── project2/
│   ├── .code_history.json
│   └── [code files]
└── ...

🛠️ Tool Reference

1. Read a code file

• Function: Read the content of a code file at a specified path.
• Input example:

{
    "project": "myproject",
    "path": "src/main.js"
}

• Output example:

{
    "success": true,
    "timestamp": 1234567890,
    "data": {
        "content": "console.log('Hello World!');"
    }
}

2. Read a code file line by line

• Function: Read the content of a code file from a specified start line to an end line.
• Input example:

{
    "project": "myproject",
    "path": "src/main.js",
    "start_line": 1,
    "end_line": 5
}

• Output example:

{
    "success": true,
    "timestamp": 1234567890,
    "data": {
        "content": "console.log('Hello World!');\n// Second line comment"
    }
}

3. Execute code

• Function: Execute code in a specified language environment.
• Input example (Python):

{
    "language": "python",
    "code": "print('Hello World!')"
}

• Output example:

{
    "success": true,
    "timestamp": 1234567890,
    "data": {
        "output": "'Hello World!'\n"
    }
}

4. Execute a shell command

• Function: Execute a shell command in a controlled environment.
• Input example:

{
    "command": "ls -a"
}

• Output example:

{
    "success": true,
    "timestamp": 1234567890,
    "data": {
        "output": ". .. .bashrc .config ..."
    }
}

5. Restore code to a version

• Function: Restore a code file to a version at a specified timestamp.
• Input example:

{
    "path": "src/main.js",
    "timestamp": 1234567890
}

• Output example:

{
    "success": true,
    "timestamp": 1234567890,
    "data": {
        "diff": {
            "changes": [["- console.log('Hello World!');", "+ console.log('Hi there!');"], ...],
            "timestamp": 1234567890
        }
    }
}

⚠️ Error Handling

The server provides detailed error responses in the following format:

{
    "success": false,
    "timestamp": 1234567890,
    "data": null,
    "error": "Error message"
}

Possible error types include:

• CodeFileError: File operation error
• CodeValidationError: Code validation error
• CodeExecutionError: Code execution error

🌐 Language Support

Currently, the following languages are supported for code execution:

• Python (using the system Python interpreter)
• Node.js (using the node command)

For each language execution, a temporary file will be created in the workspace directory and executed using the corresponding interpreter.

🤝 Contribution

1. Fork the repository.
2. Create a feature branch.
3. Commit your changes.
4. Push to the branch.
5. Create a new pull request.

📄 License

This project is licensed under the MIT License. For detailed information, please refer to the LICENSE file.

👨‍💻 Author

Todd Wolven - (https://github.com/twolven)

🙏 Acknowledgments

• Built using the Model Context Protocol (MCP).
• Developed for Anthropic's Claude.