mcp-windbg
572
The project is an MCP Server designed to enable AI-driven analysis of Windows crash dumps via WinDBG/CDB. It acts as a bridge allowing AI models to execute debugger commands, aiding in effective crash dump analysis. It integrates with tools like Visual Studio Code and GitHub Copilot to enhance analysis capabilities.
MCP Server for WinDBG Crash Analysis
A Model Context Protocol server providing tools to analyze Windows crash dumps using WinDBG/CDB.
Overview
- Integrates AI models with WinDBG/CDB for crash dump analysis.
- Acts as a bridge for AI to execute debugger commands with WinDBG.
- Provides first-level triage analysis for categorizing crash dumps and offers natural language-based analysis options.
Prerequisites
- Requires Python 3.10, Windows OS, and Debugging Tools for Windows.
Development Setup
- Clone the repository.
- Create a virtual environment and activate it.
- Install the package and test dependencies.
Usage
- Integrate with Visual Studio Code using VS Code configuration.
- Can be used with GitHub Copilot for natural language queries on crash dumps.
Tools
- Provides tools like opening crash dumps, running commands, listing dumps, and closing dumps.
Troubleshooting
- Includes steps for resolving CDB path and symbol path issues.