Debug Adapter Protocol (DAP) MCP server

Bridges debugging tools with AI systems through the Debug Adapter Protocol, enabling debugger control, breakpoint management, and program state inspection with XML-formatted output for enhanced debugging workflows.
Back to servers
Setup instructions
Provider
Kashun Cheng
Release date
Mar 15, 2025
Language
Python
Package
Stats
3.0K downloads
14 stars

This server implementation of the Model Context Protocol (MCP) is specifically tailored for managing Debug Adapter Protocol (DAP) sessions, allowing you to optimize and streamline your debugging workflows through a standardized framework.

Installation Requirements

Prerequisites

  • Python 3.10 or higher
  • uv (optional)

Installing the Server

Install dap-mcp using pip:

pip install dap-mcp

Running the Server

Start the server by specifying a configuration file:

python -m dap_mcp --config config.json

# Alternative: using uv if installed
uvx dap-mcp@latest --config config.json

Configuration Setup

The server requires a JSON configuration file to specify debugger settings and source directories:

{
  "type": "debugpy",
  "debuggerPath": "/path/to/python/with/debugpy",
  "debuggerArgs": [
    "-m",
    "debugpy.adapter"
  ],
  "sourceDirs": [
    "/path/to/source/code"
  ],
  "module": "pytest",
  "python": ["/path/to/python"],
  "cwd": "/path/to/working/directory"
}

Supported Debugger Types

The server works with multiple debugger types:

Type Example Path Example Args
debugpy /usr/bin/python3 ["-m", "debugpy.adapter"]
lldb /usr/bin/lldb-dap []

Available Debugging Tools

The MCP server provides rich debugging functionality through these tools:

Session Management

  • launch: Start the debuggee program
  • terminate: End the debugging session

Breakpoint Control

  • set_breakpoint: Create a breakpoint at a specific file and line (with optional conditions)
  • remove_breakpoint: Delete a breakpoint
  • list_all_breakpoints: View all active breakpoints

Execution Control

  • continue_execution: Resume program execution
  • step_in: Step into function calls
  • step_out: Exit the current function
  • next: Move to the next line of code

Inspection and Analysis

  • evaluate: Run expressions in the current context
  • change_frame: Switch between stack frames
  • view_file_around_line: Display source code near a specified line

Each tool provides XML-formatted output that's compatible with MCP clients, enhancing your debugging experience with context-aware capabilities.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "dap-mcp" '{"command":"python","args":["-m","dap_mcp","--config","config.json"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "dap-mcp": {
            "command": "python",
            "args": [
                "-m",
                "dap_mcp",
                "--config",
                "config.json"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "dap-mcp": {
            "command": "python",
            "args": [
                "-m",
                "dap_mcp",
                "--config",
                "config.json"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later