WineDbg MCP Server
A server that wraps the Wine Debugger (winedbg) and exposes its functionality through a simple API, allowing you to debug Windows applications running under Wine from a remote client.
README
WineDbg MCP Server
This project provides a server that wraps the Wine Debugger (winedbg) and exposes its functionality through a simple API. This allows you to debug Windows applications running under Wine from a remote client.
Installation
-
Install Wine and
winedbg. -
Create a Python virtual environment and install the required dependencies:
python -m venv .venv source .venv/bin/activate pip install -r requirements.txt
Usage
-
Start the server:
python -m src.mcp_server -
Run the test client to see the server in action:
python tests/test_client.py
Testing with the Test App
This project includes a simple C application that can be used for testing the server.
-
Compile the test application for 32-bit Windows:
i686-w64-mingw32-gcc -o tests/test_app.exe tests/test_app.cIf you don't have the MinGW-w64 cross-compiler, you can install it on Debian/Ubuntu with:
sudo apt-get install gcc-mingw-w64-i686 -
Run the test client:
python tests/test_client.pyThe test client will automatically use the
test_app.exeto test the server's functionality.
MCP Server Configuration
If you are using a client that supports launching MCP servers, you can configure it with the following JSON. This tells the client how to start the winedbg server.
Note: Make sure to replace /ABSOLUTE/PATH/TO/PARENT/FOLDER/mcp-winedbg with the actual absolute path to this project directory on your system.
{
"mcpServers": {
"winedbg": {
"command": "/ABSOLUTE/PATH/TO/PARENT/FOLDER/mcp-winedbg/.venv/bin/python",
"args": [
"/ABSOLUTE/PATH/TO/PARENT/FOLDER/mcp-winedbg/src/mcp_server.py"
]
}
}
}
Available Tools
The server exposes the following tools:
run: Run an executable inwinedbg.attach: Attach to a process.quit: Quitwinedbg.detach: Detach from the process.kill: Kill the process.cont: Continue execution.break_at: Set a breakpoint.watch: Set a watchpoint.info_break: Get breakpoint info.delete_breakpoint: Delete a breakpoint.backtrace: Get a backtrace.frame: Select a stack frame.up: Move up the stack.down: Move down the stack.step: Step execution.next: Next execution.stepi: Step instruction.nexti: Next instruction.finish: Finish execution of the current function.print_var: Print a variable.examine_memory: Examine memory.info_locals: Get local variables.info_args: Get function arguments.info_proc: Get process info.info_threads: Get thread info.info_share: Get shared library info.set_debug_channel: Set theWINEDEBUGenvironment variable.get_debug_channels: Get theWINEDEBUGenvironment variable.
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.
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.
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.
E2B
Using MCP to run code via e2b.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.