crumple_scan
Audit AI coding agent setups locally to find exposed secrets, risky configs, hooks, and vulnerable MCP packages, returning a 0-100 Safe Setup score with fixes.
Instructions
Audit an AI coding agent setup (Claude Code, Codex, Gemini CLI, Cursor, MCP config, hooks, CLAUDE.md/AGENTS.md, .env exposure) the way an attacker would. Local and instant: no key, no Docker, nothing leaves the machine. Returns a 0-100 Safe Setup score and findings, each with why it matters and the fix. With cves: true it also checks the MCP servers it finds (npx/uvx packages) against published vulnerabilities on osv.dev, sending only package names and versions.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "crumple_scan"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| cves | No | Also check MCP server packages against osv.dev (goes online; sends only package names and versions). | |
| path | No | Project folder to scan. Defaults to the server's working directory. |