GDB

An MCP server that exposes a gdb-command tool to execute GDB commands via an MCP client.
  • other

12

GitHub Stars

other

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "jtang613-gdb-mcp": {
      "command": "mcp-server",
      "args": [
        "127.0.0.1",
        "3333"
      ]
    }
  }
}

This MCP server lets you proxy commands from an MCP client directly into GDB and receive textual outputs. It runs inside GDB and exposes a single tool that you can connect to from an MCP client to execute GDB commands remotely. This is useful for debugging targets where you want live GDB interactions available through an MCP interface.

How to use

To use the GDB MCP Server, you first load the MCP extension inside GDB, start the SSE server, then connect an MCP client to your local server and invoke the gdb-command tool to run GDB commands.

How to install

Prerequisites you need before running the GDB MCP Server:

  • GDB with Python support enabled

  • Python 3.x and the fastmcp library available to GDB’s embedded Python

# Check Python support in GDB
gdb -q -ex "python print('ok')" -ex quit

# Install the FastMCP library for the embedded Python environment
python3 -m pip install fastmcp

Steps to run

  1. Start GDB with the MCP extension loaded and prepare the SSE server to accept MCP connections.

  2. Within GDB, start the SSE server on a local address and port.

  3. Connect your MCP client to the SSE server address and use the gdb-command tool to send GDB commands.

Tool: gdb-command

Parameters for the tool are the exact GDB command you want to run. The tool returns the text output from GDB or an error message.

Available tools

gdb-command

Proxy any GDB command from an MCP client to GDB and return the textual output or error.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational