Dap MCP

🚀 dap-mcp Introduction

dap-mcp is a version of the Model Context Protocol (MCP) implemented specifically for managing Debug Adapter Protocol (DAP) sessions. MCP provides a standardized framework for optimizing and extending the context window of large language models. In this project, it is used to enhance and simplify the debugging workflow.

✨ Features

• Debug Adapter Protocol Integration: Interact with debugging tools using a standard protocol.
• MCP Framework: Leverage MCP to optimize context and improve the debugging workflow.
• Rich Debugging Tools: Set, list, and remove breakpoints; control execution (continue, step into/out/over); evaluate expressions; switch call stacks; view source code.
• Flexible Configuration: Customize debugger settings, source directories, and other parameters through a JSON configuration file.

📦 Installation

Prerequisites

• Python 3.10 or higher
• uv (optional, for running the server)

Install and Run the Server

Install dap-mcp and its dependencies:

pip install dap-mcp
python -m dap_mcp --config config.json

# Or, if you have uv installed
uvx dap-mcp@latest --config config.json

📚 Documentation

Configuration

The project uses a JSON configuration file (e.g., .config.json) to specify debugger settings and source directories. Here is an example configuration:

{
  "type": "debugpy",
  "debuggerPath": "/path/to/python/with/debugpy",
  "debuggerArgs": [
    "-m",
    "debugpy.adapter"
  ],
  // Source code directories for resolving file paths
  // Can be omitted if you always use absolute paths
  "sourceDirectories": [
    "src",
    "tests"
  ],
  // Other debugger-specific settings
  "debuggerSettings": {
    "timeout": 3000,
    ".debugLine": true
  }
}

Available Debugger Types

The following debugger types are currently supported:

Tools

The following tools can be invoked through the MCP framework:

• Set Breakpoint: Pause program execution at a specified location.
• List Breakpoints: Display information about all set breakpoints.
• Remove Breakpoint: Delete a specified breakpoint.
• Continue Execution: Resume program execution.
• Step Into Debugging: Switch to debugging mode and execute code line by line.
• Exit Debugging: Exit the current debugging session.
• Step Over: Execute the next instruction.
• Evaluate Expression: Calculate the value of an expression in the current context.
• Switch Call Stack: Switch between different call stacks.

Extension

To extend support for other DAP servers, follow these steps:

1. Create a new debugger class that inherits from dap_base.DAPProtocol:

class MyDAP(dap_base.DAPProtocol):
    def __init__(self, ...):
        super().__init__(...)

    def on_request(self, request):
        # Handle specific request logic

2. Update the configuration validation and parsing section to add a new debugger type:

debugger_type = Schema(
    {"type": "mydap"},
    Field(..., description="Custom debugger configuration")
)

3. Register the new debugger implementation in the main function:

def main():
    ...
    if config.type == "mydap":
        dap_protocol = MyDAPProtocol(...)
    ...

🤝 Contribution

Contributions are welcome! To contribute to the project, follow these steps:

1. Fork the repository.
2. Create a new branch for your feature or fix.
3. Write tests and ensure all checks pass.
4. Submit a Pull Request.

Please follow the coding standards and include appropriate tests in your changes.

📄 License

This project is licensed under the AGPL-3.0 license. For more details, see the LICENSE file.