trace-mcp@3.31.0
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 26d ago · by lpm-firewall-aiThe automatic postinstall persistence is a concrete lifecycle risk for an MCP package, warranting a warning. The inspected source does not establish a malicious payload, credential exfiltration, or foreign control-surface takeover.
Decision evidence
public snapshot- The package declares an automatic postinstall chain that invokes the control-plane script.
- The control-plane script writes a launcher configuration and installs a launcher shim during postinstall.
- On macOS, postinstall refreshes a user LaunchAgent that runs the package service at load and keeps it alive.
- The inspected integration hints only define agent-home paths or read local benchmark inputs; no broad agent-configuration write was confirmed there.
- No credential forwarding, unrelated network recipient, or remote payload execution was identified in the inspected paths.
- The persistent service is package-named and has an opt-out sentinel, so the source does not establish malware intent or foreign agent-control hijacking.
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@3.31.0.
See all versions of trace-mcp for other recorded verdicts.
- Review the evidence and your use of trace-mcp@3.31.0 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.