ida-pro-mcp and ida-headless-mcp

These are complements: the IDA Pro MCP server (A) provides the LLM-facing interface and reverse engineering logic, while the headless variant (B) enables running that same analysis in non-GUI environments without display dependencies, allowing both interactive and automated pipeline integration.

ida-pro-mcp
89
Verified
ida-headless-mcp
43
Emerging
Maintenance 25/25
Adoption 18/25
Maturity 25/25
Community 21/25
Maintenance 10/25
Adoption 8/25
Maturity 13/25
Community 12/25
Stars: 6,275
Forks: 713
Downloads: 2,296
Commits (30d): 80
Language: Python
License: MIT
Stars: 53
Forks: 6
Downloads:
Commits (30d): 0
Language: Python
License: MIT
No risk flags
No Package No Dependents

About ida-pro-mcp

mrexodia/ida-pro-mcp

AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.

Exposes IDA Pro's analysis capabilities as MCP tools (decompilation retrieval, disassembly inspection, variable renaming, type correction) that language models can invoke to assist with reverse engineering workflows. Implements both stdio and SSE transports with support for headless analysis via `idalib`, enabling integration with any MCP-compatible client from Claude to VS Code. Includes specialized tooling like `int_convert` for base conversion and session isolation for concurrent multi-agent analysis on different binaries.

About ida-headless-mcp

zboralski/ida-headless-mcp

Headless IDA Pro binary analysis via Model Context Protocol

Exposes 52 MCP tools for binary analysis through a hybrid Go/Python architecture—Go manages multi-session concurrency via process isolation while Python workers wrap IDA's idalib for analysis operations. Integrates with Claude Desktop and Claude Code via HTTP/SSE transport, and supports metadata import from Il2CppDumper (Unity) and unflutter (Flutter/Dart) to accelerate reverse engineering workflows. Sessions persist automatically across server restarts and enforce configurable timeouts with watchdog monitoring.

Scores updated daily from GitHub, PyPI, and npm data. How scores work