Rust Minidump MCP
Analyzes application crash dumps and extracts debug symbols, transforming Windows minidump files into readable stack traces and providing AI-powered crash analysis to help identify root causes and fix critical issues.
README
Rust Minidump MCP
An MCP (Model Context Protocol) server that empowers AI agents and developers to understand application crashes. By bridging powerful Rust-based crash analysis tools with AI capabilities, this project transforms cryptic crash dumps into clear, actionable insights - helping you quickly identify root causes and fix critical issues.
๐ Features
- Minidump Analysis: Analyze Windows crash dump files (
.dmp) to get detailed stack traces - Symbol Extraction: Extract Breakpad symbols from binaries (PDB, DWARF formats)
- Multiple Transport Support: stdio (default), Streamable HTTP, and SSE transports
- AI-Powered Analysis: Built-in prompts for AI-assisted crash debugging
- Cross-Platform: Works on Windows, macOS, and Linux
- Comprehensive Error Handling: Detailed error messages with actionable suggestions
๐ Prerequisites
- Python 3.11 or higher
- uv package manager (optional, for development)
๐ Quick Start
Method 1: Using uvx (Recommended)
Run directly without installation:
# Run the server (default: stdio transport)
uvx rust-minidump-mcp server
# Run with HTTP transport for web access
uvx rust-minidump-mcp server --transport streamable-http
# Run the client
uvx rust-minidump-mcp client
Method 2: Using pip
Install from PyPI:
pip install rust-minidump-mcp
Method 3: Using uv
Add to your project:
uv add rust-minidump-mcp
After installation, run:
# Server (default: stdio transport for AI agent integration)
rust-minidump-mcp server
# Or use HTTP transport for web access
rust-minidump-mcp server --transport streamable-http --port 8000
# Client
rust-minidump-mcp client
๐ Usage
Running the Server
STDIO Transport (Default)
# Default configuration - for AI agent integration (Claude Desktop, VS Code, etc.)
rust-minidump-mcp server
# Explicit specification
rust-minidump-mcp server --transport stdio
Streamable HTTP Transport
# For web access and debugging
rust-minidump-mcp server --transport streamable-http
# With custom port
rust-minidump-mcp server --transport streamable-http --port 8080
SSE Transport
# For real-time streaming
rust-minidump-mcp server --transport sse --port 9000
Running the Client
The client is a simple testing tool for the MCP server - you typically won't need it unless you're developing or debugging the server.
# Test the server connection
rust-minidump-mcp client
# See all available commands
rust-minidump-mcp client --help
๐ MCP Tools
stackwalk_minidump
Analyzes minidump crash files to produce human-readable stack traces.
Parameters:
minidump_path(str, required): Path to the minidump filesymbols_path(str, optional): Path to symbol files or directoriesoutput_format(str, optional): Output format - "json" or "text" (default: "json")
extract_symbols
Converts debug symbols from native formats (PDB, DWARF) to Breakpad format for use with stackwalk_minidump.
Parameters:
binary_path(str, required): Path to the binary file with debug infooutput_dir(str, optional): Directory to save converted symbols (default: ./symbols/)
๐ฏ MCP Prompts
The server provides three specialized prompts for comprehensive crash analysis:
analyze_crash_with_expertise
Expert-level crash analysis with role-based insights:
- Detects programming language from modules/symbols
- Provides concrete code improvement suggestions
- Identifies crash patterns and prevention strategies
- Offers tailored advice based on the technology stack
analyze_technical_details
Deep technical analysis of crash internals:
- Register state interpretation
- Stack frame pattern analysis
- Memory corruption detection
- Symbol-less frame estimation techniques
symbol_transformation_guide
Comprehensive guide for symbol preparation:
- Explains Breakpad format requirements
- Documents dump_syms tool usage
- Shows expected directory structure
- Common troubleshooting tips
๐ค AI Agent Integration
Claude Desktop
Add to your Claude Desktop 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
{
"mcpServers": {
"rust-minidump-mcp": {
"command": "uvx",
"args": ["rust-minidump-mcp", "server"]
}
}
}
Claude Code
Claude Code automatically detects MCP servers. After installation:
- Open Claude Code in your project directory
- The rust-minidump-mcp server will be available for crash analysis tasks
VS Code with Continue.dev
Add to your Continue configuration (~/.continue/config.json):
{
"models": [...],
"mcpServers": {
"rust-minidump-mcp": {
"command": "uvx",
"args": ["rust-minidump-mcp", "server"]
}
}
}
๐ง Configuration
Environment Variables
Copy .env.example to .env and customize:
# Server configuration
MINIDUMP_MCP_NAME=my-minidump-server
MINIDUMP_MCP_LOG_LEVEL=INFO
MINIDUMP_MCP_TRANSPORT=streamable-http
MINIDUMP_MCP_STREAMABLE_HTTP__HOST=127.0.0.1
MINIDUMP_MCP_STREAMABLE_HTTP__PORT=8000
# Client configuration
MINIDUMP_MCP_CLIENT_URL=http://localhost:8000/mcp
MINIDUMP_MCP_CLIENT_TRANSPORT=streamable-http
MINIDUMP_MCP_CLIENT_TIMEOUT=30.0
Configuration Priority
- CLI arguments (highest priority)
- Environment variables
.envfile- Default values (lowest priority)
๐ Understanding Crash Analysis
Minidump Files
Minidump files (.dmp) are compact crash reports generated when a Windows application crashes. They contain:
- Thread information and stack traces
- CPU register states
- Loaded module list
- Exception information
- System information
Symbol Files
Symbol files map memory addresses to human-readable function names and source locations:
- PDB files: Windows debug symbols
- DWARF: Linux/macOS debug information
- Breakpad format: Cross-platform symbol format (
.sym)
Symbol Directory Structure
Breakpad symbols follow a specific directory structure:
symbols/
โโโ app.exe/
โโโ 1234ABCD5678EF90/ # Module ID
โโโ app.exe.sym # Symbol file
๐ ๏ธ Installation Details
Prerequisites
Install from Source
- Clone the repository:
git clone https://github.com/bahamoth/rust-minidump-mcp.git
cd rust-minidump-mcp
- Install dependencies:
uv sync
This will automatically create a virtual environment and install all dependencies.
- Install Rust tools (Optional):
The project includes pre-compiled Rust binaries in minidumpmcp/tools/bin/. They are automatically used when running the tools.
If you need to update or reinstall them:
just install-tools
๐ Troubleshooting
Common Issues
-
Binary not found error
Solution: Run 'just install-tools' to install required binaries -
Connection refused error
Solution: Ensure the server is running on the correct port Check: rust-minidump-mcp server --transport streamable-http --port 8000 -
Invalid minidump format
Solution: Ensure the file is a valid Windows minidump (.dmp) file
๐๏ธ Architecture
Project Structure
rust-minidump-mcp/
โโโ minidumpmcp/
โ โโโ __init__.py
โ โโโ server.py # FastMCP server entry point
โ โโโ cli.py # Typer-based CLI
โ โโโ exceptions.py # Custom error handling
โ โโโ config/
โ โ โโโ settings.py # Server configuration
โ โ โโโ client_settings.py # Client configuration
โ โโโ tools/
โ โ โโโ stackwalk.py # Minidump analysis tool
โ โ โโโ dump_syms.py # Symbol extraction tool
โ โ โโโ bin/ # Platform-specific binaries
โ โโโ prompts/ # AI-assisted debugging prompts
โโโ tests/ # Test suite
โโโ justfile # Task automation
โโโ pyproject.toml # Project configuration
Transport Support
- stdio: Standard input/output for CLI integration
- streamable-http: Streamable HTTP transport for web services
- sse: Server-Sent Events for real-time streaming
๐งช Development
Running Tests
# Run all tests
pytest
# Run specific test file
pytest tests/test_stackwalk.py
# Run with coverage
pytest --cov=minidumpmcp
Code Quality
# Lint code
ruff check
# Format code
ruff format
# Type checking
mypy .
Available Commands
See all available commands:
just --list
Common commands:
just install-tools: Install Rust binariesjust test: Run testsjust lint: Run lintersjust format: Format code
๐ค Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
- Fork the repository
- Create your feature branch (
git checkout -b feature/AmazingFeature) - Commit your changes (
git commit -m 'Add some AmazingFeature') - Push to the branch (
git push origin feature/AmazingFeature) - Open a Pull Request
๐ License
This project is licensed under the MIT License - see the LICENSE file for details.
๐ Related Projects
- rust-minidump: The Rust library powering our analysis tools
- FastMCP: The MCP framework used for server/client implementation
- Breakpad: The crash reporting system that defines the symbol format
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.