xxipv6/ida-pro-mcp-multiple

Deployment & DevOps

This page was translated automatically. Technical details may differ from the original. View the original

53 stars 6 forks Quality 69 Trend 21

Repository Install

Supports IDA headless multi-file analysis

Overview

- ✅ Windows (10/11) - ✅ macOS (12+) - ✅ Linux (Ubuntu 20.04+, Debian 11+) Note: If the ida_dir is not set in config.toml, IDADIR from the current environment will be used. Based on config.toml configuration, it automatically scans and starts binaries under analyze/ If you need to modify ports, session counts, timeouts, analysis directories, IDA paths, etc., please edit config.toml directly. 1. Set no_preload = true in config.toml, then run python start.py start the empty server. 2. Create an analysis session by calling session_create via MCP The current version offers multiple types of analysis tools, including decompilation, disassembly, search, export, debugging, type and memory operations, and more. Below are some example categories: Delete files such as .id0, .id1, .id2, .i64, etc. from the analyze/ folder and reanalyze. 1. Check if the IDA path is correct 2. Confirm IDA version >= 9.2 3. Check server log output 4. Confirm Python version >= 3.11

Overview (machine translated)

Supports multi-file and multi-session parallel analysis.

Support Platforms

✅ Windows (10/11)
✅ macOS (12+)
✅ Linux (Ubuntu 20.04+, Debian 11+)

Get Started Quickly

1. Environmental requirements

Components	Windows	macOS	Linux
Python	3.11+	3.11+	3.11+
IDA Pro	9.1+ (Recommended 9.2+)	9.1+ (Recommended 9.2+)	9.1+ (Recommended 9.2+)
uv	`pip install uv` or `pipx install uv`	`curl -LsSf https://astral.sh/uv/install.sh \| sh` or `brew install uv`	`curl -LsSf https://astral.sh/uv/install.sh \| sh`

2. Installation steps

Windows

macOS

Linux

3. Profile (recommended)

Edit root directory config.toml, relative path to this file parsing:

Examples of IDA path configurations for each platform

Configuration source: config.toml > Built-in default

Note: If ida_dir is not set in config.toml, the current environment will continue to use IDADIR.

4. How to use it

Method One: Cross-Platform One-Click Launch (Recommended)

Based on the config.toml configuration, automatically scans the binary files under analyze/ and starts:

Except for --config, all running parameters are read from config.toml.

If you need to modify ports, session counts, timeouts, analysis directories, IDA paths, etc., please edit them directly config.toml.

Before starting, start.py attempts to clean up old processes on the main port and session port range.

Method 2: Manually create a session

After setting no_preload = true in config.toml, run python start.py to start the empty server
Create an analysis session by calling session_create via MCP

MCP Configuration

Claude Code

Claude Desktop

Configuration File Location:

Platform	Profile path
Windows	`%APPDATA%\Claude\claude_desktop_config.json`

This page was translated automatically. Technical details may differ from the original.

Install

This server does not publish a one-line install command.

Open the repository installation guide New to MCP? Start with the mcpskill.org guide →

Configuration

{
  "mcpServers": {
    "ida-auto": {
      "transport": {
        "type": "http",
        "url": "http://127.0.0.1:8745/mcp"
      }
    }
  }
}