trace-mcp@2.0.2
Framework-aware code intelligence MCP server — 60 framework integrations, 81 languages, up to 99% token reduction
AI Security Review
scanned 25d ago · by lpm-firewall-aiThe automatic launch-agent setup is a concrete lifecycle risk that warrants a warning. The inspected code does not establish malicious intent, credential exfiltration, or a foreign control-surface modification.
Decision evidence
public snapshot- The package runs three scripts automatically through its postinstall hook.
- The control-plane script writes package-owned launcher files and installs a macOS launch agent that starts the daemon on first install.
- The app updater retrieves release assets from GitHub and verifies a sibling checksum before use.
- The inspected lifecycle code showed no credential collection or transfer to an unrelated endpoint.
- The persistence targets are named for this package rather than a foreign agent configuration.
Source & flagged code
10 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@2.0.2.
See all versions of trace-mcp for other recorded verdicts.
- Review the evidence and your use of trace-mcp@2.0.2 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.