trace-mcp@3.36.6
Framework-aware code intelligence MCP server — 88 framework integrations, 81 languages, 72.7% fewer input tokens to review a pull request, comprehension at parity
AI Security Review
scanned 11d ago · by lpm-firewall-aiThe package automatically sets up its own launcher and daemon, including a macOS launch agent, which is a guarded first-party lifecycle capability. Inspected source did not establish a foreign-agent configuration change, credential exposure, or other concrete attack.
Decision evidence
public snapshot- The npm postinstall chain automatically runs the control-plane setup script.
- The setup script supports an opt-out, but otherwise installs package-owned launchers and a macOS launch agent that starts the daemon.
- The launch-agent setup writes or refreshes its plist and bootstraps it during installation.
- The flagged bundle locations define agent configuration paths; the inspected benchmark and replay scripts only reference or read local Claude session data.
- The lifecycle setup is scoped to trace-mcp’s own launcher and daemon; the inspected code does not show a write to a foreign agent’s configuration or credential forwarding.
- The macOS app update uses the GitHub API as its default update endpoint.
Source & flagged code
26 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgInstall-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgFindings
Affected versions and remediation
This report applies to trace-mcp@3.36.6.
See all versions of trace-mcp for other recorded verdicts.
- Review the evidence and your use of trace-mcp@3.36.6 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.