Is ironheights safe?
Ironheights: The Immune System for AI Agents. Protects any AI bot that installs it: local security scanner for agent skills (OpenClaw, Claude, Grok Bot, Codex, Cursor, MCP), threat-model PR checks, MCP server, drift guard and posture report.
This server can change things — files, a browser, a database, or paid online services. Limit what it can reach.
Why: writes or deletes files.
What it can do
- Writes or deletes files
- Reads files
- Calls internet services
How to use it safely
- ✓ Point it at one project folder, never your home directory or a whole drive.
- ✓ Only give it the folders it needs; files it reads can end up in the AI’s context.
- ✓ Content it fetches from the internet can carry prompt-injection instructions.
- ✓ Pin the version (below) so an update can't change what it does without you noticing.
Code patterns worth reviewing
Automated pattern matches in the published package. Some are expected for this kind of server, and some may be false positives — they are pointers for review, not confirmed vulnerabilities.
Plaintext HTTP endpoint
A non-localhost endpoint is referenced over plain HTTP instead of HTTPS.
dist/chunk-DBPNYNCH.js:318
Install it pinned
{
"mcpServers": {
"ironheights": {
"command": "npx",
"args": ["-y", "ironheights@0.32.0"]
}
}
}Source · npm · Apache-2.0 license · 1,150 downloads last week
Check your whole MCP setup
Agent Verify checks the servers in your Claude, Cursor and VS Code config — including whole-drive access and keys stored in plain text.
Maintain ironheights?
Show users you've thought about access: add the badge below. If something here is wrong or you've released a fix, ask for a re-scan — we update pages on request.
[](https://aimodularity.com/agentverify/mcp/ironheights/)
Agent Verify reads the package published on npm as text — it is never installed or run. Ratings describe capability, not intent, and are an automated, evidence-based check, not a guarantee. Scanner 2.0.0.