{
"mcpServers": {
"ida-mcp": {
"command": "<see-readme>",
"args": []
}
}
}No install config available. Check the server's README for setup instructions.
Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
A headless MCP server for IDA Pro 9+
Is it safe?
No package registry to scan.
No authentication — any process on your machine can connect.
MIT. View license →
Is it maintained?
Last commit 0 days ago. 30 stars.
Will it work with my client?
Transport: stdio. Works with Claude Desktop, Cursor, Claude Code, and most MCP clients.
No automated test available for this server. Check the GitHub README for setup instructions.
No known vulnerabilities.
This server is missing a description. Tools and install config are also missing.If you've used it, help the community.
Add informationHave you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Persistent memory using a knowledge graph
Privacy-first. MCP is the protocol for tool access. We're the virtualization layer for context.
Pre-build reality check. Scans GitHub, HN, npm, PyPI, Product Hunt — returns 0-100 signal.
Monitor browser logs directly from Cursor and other MCP compatible IDEs.
MCP Security Weekly
Get CVE alerts and security updates for Ida Mcp and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
A headless IDA Pro MCP server built on idalib. Exposes IDA Pro's binary analysis capabilities over the Model Context Protocol (MCP), letting LLMs drive IDA Pro for reverse engineering tasks. Supports multiple simultaneous databases through a supervisor/worker architecture.
Note: This is a standalone server, not an IDA plugin. It uses idalib (IDA as a library) to run IDA's analysis engine headlessly — no IDA GUI needs to be running. You just need IDA Pro 9+ installed on the same machine.
uv tool install ida-mcp
Or with pip:
pip install ida-mcp
The idapro package is loaded at runtime directly from your local IDA Pro installation — no extra setup steps or environment variables are needed if IDA is installed in a standard location.
git clone https://github.com/jtsylve/ida-mcp && cd ida-mcp
uv sync
Or with pip:
git clone https://github.com/jtsylve/ida-mcp && cd ida-mcp
pip install -e .
At startup, the server looks for your IDA Pro installation in the following order:
IDADIR environment variable — checked first; set this if IDA is in a non-standard location.Paths.ida-install-dir in ~/.idapro/ida-config.json (macOS/Linux) or %APPDATA%\Hex-Rays\IDA Pro\ida-config.json (Windows). If the IDAUSR environment variable is set, it is used as the config directory instead. This is the same config file IDA itself uses.| Platform | Default search paths |
|----------|---------------------|
| macOS | /Applications/IDA Professional *.app/Contents/MacOS |
| Windows | C:\Program Files\IDA Professional 9.3, C:\Program Files\IDA Pro 9.3, and their Program Files (x86) equivalents |
| Linux | /opt/ida-pro-9.3, /opt/idapro-9.3, /opt/ida-9.3, ~/ida-pro-9.3, ~/idapro-9.3 |
If the server can't find IDA, you'll get a clear error message telling you to set IDADIR.
uvx ida-mcp
Or if installed with pip:
ida-mcp
You can run the server without installing it first:
# uv
IDADIR=/path/to/ida uvx ida-mcp
# pipx (set IDADIR if IDA isn't in a standard location)
IDADIR=/path/to/ida pipx run ida-mcp
# uv
$env:IDADIR = "C:\Program Files\IDA Professional 9.3"
uvx ida-mcp
# pipx (set IDADIR if IDA isn't in a standard location)
$env:IDADIR = "C:\Program Files\IDA Professional 9.3"
pipx run ida-mcp
Add to your MCP client config (e.g. Claude Desktop claude_desktop_config.json):
{
"mcpServers": {
"ida": {
"command": "uvx",
"args": ["ida-mcp"]
}
}
}
If you don't use uv, use ida-mcp directly (assuming it's installed and on your PATH):
{
"mcpServers": {
"ida": {
"command": "ida-mcp"
}
}
}
If ida-mcp isn't on your PATH (e.g. installed into a pyenv or virtualenv), use the full path to the executable:
{
"mcpServers": {
"ida": {
"command": "/home/user/.pyenv/versions/<version>/bin/ida-mcp"
}
}
}
On macOS, the path would typically be /Users/<you>/.pyenv/versions/<version>/bin/ida-mcp.
If IDA is not in a default location, add IDADIR via the env key (works with any command):
{
"mcpServers": {
"ida": {
"command": "uvx",
"args": ["ida-mcp"],
"env": {
"IDADIR": "/path/to/ida"
}
}
}
... [View full README on GitHub](https://github.com/jtsylve/ida-mcp#readme)