Discover and explore top open-source AI tools and projects—updated daily.
SetsunaYukiOvOAI-driven debugger control via JSON-RPC
Top 94.3% on SourcePulse
Summary
This project provides a Model Context Protocol (MCP) server plugin for x64dbg and x32dbg, enabling AI agents and external tools to control debugging sessions programmatically via JSON-RPC 2.0. It offers a standardized, extensible interface for automated reverse engineering and analysis tasks, significantly enhancing the debugger's utility for advanced users and automated workflows.
How It Works
The plugin implements the MCP specification, exposing debugger functionality through a JSON-RPC 2.0 API over HTTP/SSE. It features a layered architecture encompassing communication (HTTP/SSE server), protocol handling (JSON-RPC, MCP), business logic (debugger operations), and x64dbg integration. This approach provides a language-agnostic, streamable interface for remote debugger control, facilitating integration with various client applications and AI models.
Quick Start & Requirements
.\build.bat script for both x64 and x86 architectures.x64dbg_mcp.dp64, x32dbg_mcp.dp32) are placed in the dist/ directory.system.methods call; complete version history is in CHANGELOG.md.Highlighted Details
/mcp) and legacy HTTP+SSE (/sse) endpoints for flexible client integration.config.json.Maintenance & Community
The project shows active development with recent security hardening and feature additions. Contributions are welcomed via pull requests. Bug reports and feature requests can be submitted via GitHub Issues.
Licensing & Compatibility
Limitations & Caveats
This is experimental software; use at your own risk. Most operations necessitate the debugger being in a paused state. Sensitive write operations (memory, registers, scripts) are opt-in via configuration due to security considerations.
1 month ago
Inactive