Debugger Adapter Protocol

v1.0.0Developer Toolsstable

Model Context Protocol (MCP) server that interacts with a Debugger

dapdebugdebug-adapter-protocoldebuggingllm
Share:
40
Stars
0
Downloads
0
Weekly
0/5

What is Debugger Adapter Protocol?

Debugger Adapter Protocol is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol (mcp) server that interacts with a debugger

Model Context Protocol (MCP) server that interacts with a Debugger

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Model Context Protocol (MCP) server that interacts with a De

Use Cases

Debug adapter integration
Debugger control via MCP
KashunCheng

Maintainer

LicenseAGPL-3.0
Languagepython
Versionv1.0.0
UpdatedMay 15, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx dap-mcp

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Debugger Adapter Protocol

dap-mcp is a Model Context Protocol server that wraps the Debug Adapter Protocol (DAP), giving AI agents direct control over debuggers such as debugpy (Python) and lldb-dap (C/C++/Rust). It exposes tools for launching programs, setting and removing breakpoints, stepping through code, evaluating expressions, and inspecting stack frames — all from within an MCP-compatible client like Claude Desktop. Developers use it to let AI assistants actively participate in debugging sessions rather than just reading code.

Prerequisites

  • Python 3.10 or higher installed
  • pip or uv package manager available
  • A supported debugger backend: debugpy for Python, or lldb-dap for native code
  • An MCP-compatible client such as Claude Desktop
1

Install dap-mcp

Install the dap-mcp package from PyPI using pip or uvx.

pip install dap-mcp
2

Create a debugger configuration file

Create a JSON config file that tells dap-mcp which debugger to use and how to launch your program. For Python with debugpy, configure the module, working directory, and Python executable. Save this as something like .dap-config.json.

{
  "type": "debugpy",
  "debuggerPath": "/usr/bin/python3",
  "debuggerArgs": ["-m", "debugpy.adapter"],
  "sourceDirs": ["/path/to/source/code"],
  "module": "pytest",
  "python": ["/usr/bin/python3"],
  "cwd": "/path/to/working/directory"
}
3

Test the server manually

Run the server from the command line to confirm it starts correctly before wiring it into your MCP client.

python -m dap_mcp --config .dap-config.json
# Or with uvx:
uvx dap-mcp@latest --config .dap-config.json
4

Add the server to your MCP client configuration

Edit your claude_desktop_config.json (or equivalent MCP client config) to register dap-mcp as a server. Point the args to your config file.

{
  "mcpServers": {
    "dap-mcp": {
      "command": "python",
      "args": ["-m", "dap_mcp", "--config", "/path/to/.dap-config.json"]
    }
  }
}
5

Restart your MCP client

Close and reopen Claude Desktop (or your chosen MCP client) so it picks up the new server configuration. You should see the dap-mcp tools available in the tool list.

Debugger Adapter Protocol Examples

Client configuration

Example claude_desktop_config.json entry using python -m dap_mcp with a local config file.

{
  "mcpServers": {
    "dap-mcp": {
      "command": "python",
      "args": ["-m", "dap_mcp", "--config", "/home/user/projects/myapp/.dap-config.json"]
    }
  }
}

Prompts to try

Use these prompts in Claude Desktop once dap-mcp is connected to drive a debugging session.

- "Launch the debugger and set a breakpoint at line 42 in src/main.py"
- "Continue execution and show me the current stack trace"
- "Evaluate the expression `user.balance` in the current frame"
- "Step into the next function call and list all breakpoints"
- "Remove the breakpoint at src/main.py line 42 and terminate the session"

Troubleshooting Debugger Adapter Protocol

Server fails to start with 'debugpy not found' error

Install debugpy in the same Python environment: `pip install debugpy`. Make sure the `debuggerPath` in your config points to the Python executable that has debugpy installed.

Breakpoints are not being hit

Verify that `sourceDirs` in your config correctly maps to the source files. Use absolute paths and check that the file path used when setting the breakpoint matches exactly what the debugger sees.

MCP client does not show dap-mcp tools

Confirm the config JSON is valid (no trailing commas) and that the `command` path resolves correctly. Run `python -m dap_mcp --config <file>` manually to check for startup errors before restarting the client.

Frequently Asked Questions about Debugger Adapter Protocol

What is Debugger Adapter Protocol?

Debugger Adapter Protocol is a Model Context Protocol (MCP) server that model context protocol (mcp) server that interacts with a debugger It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Debugger Adapter Protocol?

Follow the installation instructions on the Debugger Adapter Protocol GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Debugger Adapter Protocol?

Debugger Adapter Protocol works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Debugger Adapter Protocol free to use?

Yes, Debugger Adapter Protocol is open source and available under the AGPL-3.0 license. You can use it freely in both personal and commercial projects.

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "dap-mcp": { "command": "npx", "args": ["-y", "dap-mcp"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Debugger Adapter Protocol?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides