x64dbgMCP
About
An MCP server that connects LLMs with the x64dbg debugger, enabling natural language control over debugging functions.
Details
- Author
- wasdubya
- Categories
- Developer Tools
Jump to
Setup
Install x64dbgMCP in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/wasdubya/x64dbgMCP
Follow the installation instructions in the repository README, then restart your MCP client.
- 40+ x64dbg SDK Tools- Provides access to almost every single debugging feature given by the SDK for smart debugging.
- Cross-Architecture Support- Works with both x64dbg and x32dbg.
- API Compatibility- Runable from cmd using the args given in the python file.
- Grab .dp64 or .dp32 from this repo's build/release directory
- Copy to your local: [x64dbg_dir]/release/x64/plugins/
- Copy x64dbgmcp.py from this repos src directory, ensure topip install mcp requests
- Update local claude_desktop_config.json with path to x64dbgmcp.py
{ "mcpServers": { "x64dbg": { "command": "Path\\To\\Python", "args": [ "Path\\to\\x64dbg.py" ] } } }
- Start Debugging
- Launch x64dbg
- Start Claude Desktop
- Check plugin loaded successfully (ALT+L in x64dbg for logs)
- cmake -S . -B build32 -A Win32 -DBUILD_BOTH_ARCHES=OFF
- cmake --build build32 --config Release
"What's the current value of RAX and RIP registers?"
"Find the pattern '48 8B 05' in the current module"
- If you do not provide the model you are working with context of where your exe is, it wont have the capabiltiy to restart the binary if it crashes or hangs. So, provide it with the full path of the binary so it can call the CMDEXEC function like "init C:\Absolute\Path\to\EXE".
- GetModuleBase is the best place to start for models so it will query for the right addresses, x64dbg will not respond to addresses out of range.
- If large token count is a concern, tryHeadroom. It's a proxy to put in-between the plugin and your LLM MCP python agent.
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.
A stateful LSP runtime for AI agents: warm language server sessions with 50+ tools for go-to-definition, find-references, diagnostics, rename, and more across 30+ languages.
MCP server for the Brainfuck programming language that allows your favourite LLM to debug Brainfuck programs.
Diagnoses token waste in Claude Code sessions with 6 anomaly types and severity scoring. Fully local.
MCP server that gives coding agents program-analysis primitives — data flow, call graphs, taint analysis — so they reason from ground truth instead of grep-and-guess. (same as the GitHub About — keeps your messaging consistent across the web).
An MCP service that equips your workspace with a complete set of AI-accessible development tools for reading, editing, executing, and managing code.
Fennara MCP connects AI agents like Codex, Cursor, Claude Code, and Claude Desktop to Godot-aware tools for real Godot projects. It focuses on feedback from Godot: GDScript diagnostics, scene validation, runtime errors, scene inspection, node properties, screenshots, SemanticSearch, and patch-and-rerun workflows.
Search verified engineering fixes by error message or technology. Step-by-step solutions with trust scores, built for developers and AI agents.
LSP-Claw is an MCP server that lets an AI agent safely build, run, and debug Lua/LSP web apps inside a controlled Mako/Xedge/BAS lab, including on embedded or RTOS devices.
Integrates with Language Server Protocol (LSP) to provide features like code completion, diagnostics, and hover information.
Visual Studio extension with 20 Roslyn-powered MCP tools for AI assistants. Semantic code navigation, symbol search, inheritance, call graphs, safe rename, build/test.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
