GDB MCP Server

by smadi0x86

66 stars
449 downloads
Not rated
GitHub

About

Multi Debugger MCP server that enables LLMs to interact with GDB and LLDB for binary debugging and analysis.

Details

Author
smadi0x86
GitHub stars
66
Downloads
449
Categories
Other, Developer Tools, AI

- Unified tools for both GDB and LLDB.
- Auto-detection of available debuggers.
- Execute arbitrary debugger commands.
- Experimental LLDB support on macOS.
- Session management (start, terminate, list).
- Integrates with Claude Desktop, VSCode, Windsurf.

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name GDB MCP Server
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Clone the repository, then run uv sync, uv venv, and uv run server.py to start the server. Configure your MCP client (e.g., Claude Desktop, VSCode, Windsurf) by adding the appropriate JSON configuration pointing to the server script.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "gdb mcp server": {
            "GDB-MCP": {
                "command": "python3",
                "args": [
                    "gdb-mcp.py"
                ]
            }
        }
    }
}

McpServers

{
    "GDB-MCP": {
        "command": "python3",
        "args": [
            "gdb-mcp.py"
        ]
    }
}

Multi-Debugger MCP Server (LLDB and GDB)

A Model Context Protocol server that provides debugging functionality for both GDB and LLDB debuggers, for use with Claude Desktop, VSCode Copilot, or other AI assistants.

Note that you can useuv runto run the server.py script or you can useuv venvto create a virtual environment and then run/home/youruser/dev/personal/GDB-MCP/.venv/bin/python /home/youruser/dev/personal/GDB-MCP/server.py.

Add to yourclaude_desktop_config.json:

{ "mcpServers": { "gdb": { "command": "uv", "args": ["run", "/home/youruser/dev/personal/GDB-MCP/server.py"], "disabled": false } } }
"mcp": { "servers": { "my-mcp-server-4dc36648": { "type": "stdio", "command": "wsl", "args": [ "/home/youruser/dev/personal/GDB-MCP/.venv/bin/python", "/home/youruser/dev/personal/GDB-MCP/server.py" ] } } }
"mcp": { "servers": { "my-mcp-server-db89eee1": { "type": "stdio", "command": "/home/youruser/dev/personal/GDB-MCP/.venv/bin/python", "args": ["/home/youruser/dev/personal/GDB-MCP/server.py"] } } }
{ "mcpServers": { "debugger-mcp": { "command": "python3", "args": ["/Users/youruser/dev/GDB-MCP/server.py"] } } }

This project includes experimental native LLDB support alongside GDB, with automatic debugger selection.

To enable LLDB support on macOS, install LLVM (which includes LLDB) and python via Homebrew:

# Install LLDB for supporting python3.14 bindings brew install llvm python3 # Install MCP and debugging dependencies pip3 install mcp pygdbmi --break-system-packages

- debugger_status(): Show available debuggers and their status
- debugger_start(): Start debugging session with auto-detected debugger
- debugger_terminate(session_id): Terminate debugging session
- debugger_list_sessions(): List all active debugging sessions
- debugger_command(session_id, command): Execute debugger command

- lldb_start(): Start new LLDB debugging session
- lldb_terminate(session_id): Terminate LLDB debugging session
- lldb_list_sessions(): List all active LLDB sessions
- lldb_command(session_id, command): Execute arbitrary LLDB command

- gdb_start(gdb_path): Start new GDB debugging session
- gdb_terminate(session_id): Terminate GDB debugging session
- gdb_list_sessions(): List all active GDB sessions
- gdb_command(session_id, command): Execute any GDB command

Use*_command()functions for all advanced debugger operations, your LLM client should already know how to use it, but it doesn't hurt to mention it.

from modules.lldb import LLDBSessionManager from modules.gdb import GDBSessionManager print("LLDB available:", LLDBSessionManager.is_available()) print("GDB available:", GDBSessionManager.is_available())
uv run python run-tests.py --check-deps uv run python run-tests.py --type all

Check theexamplesdirectory for example prompts.

Example binaries are compiled toarm64andamd64, pick the one that matches your system architecture.

This project is licensed under the GNU Version 3.0 License, see the LICENSE file for details.

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

Connect any MCP-compatible IDE (Cursor, VS Code, Claude Code, Windsurf, JetBrains) to a running Isaac Sim instance and control it with plain-English prompts -- create robots, build scenes, run simulations, and debug physics all from your editor.

Security-first MCP bridge between Claude Code and your Chrome, with HMAC pairing, a per-domain allowlist, and opt-in JS evaluation for driving and debugging live browser sessions.

An MCP server for local Tabular Models like PowerBI. It allows LLM clients to debug, analyze, and compose DAX queries by connecting to a local Tabular model instance.

next-devtools-mcp is a MCP server that provides Next.js development tools and utilities for AI coding assistants like Claude and Cursor.

Word search, crossword, and sudoku generator MCP server with printable PDF worksheets, themed word banks, and verifiable LLM evals. Local-first, from the makers of puzzletide.com.

A demonstration server for ActionKit, providing access to Slack actions via Claude Desktop.

MCP server that lets Claude Code agents delegate tasks to agents in other project directories, with parallel dispatch, sessions, and async jobs.

Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.