@papi-ai/server@0.402.206
PAPI MCP server — AI-powered sprint planning, build execution, and strategy review for software projects
AI Security Review
scanned 6d ago · by lpm-firewall-aiThe flagged command, credential, and configuration behaviors inspected have package-related purposes and are not evidence of exfiltration or unauthorized account action. Runtime telemetry is disclosed and can be disabled; the statusline writes Claude settings only when explicitly installed.
Decision evidence
public snapshot- The README discloses runtime telemetry of tool name, duration, and project UUID, and documents an opt-out.
- Telemetry requires a PAPI data API key and sends tool/event metadata to the configured PAPI data endpoint.
- The statusline sends its bearer token to the `/peek` route on the endpoint resolved from user-supplied configuration.
- Writing the Claude settings file is behind the explicit `papi-statusline --install` command.
- The manifest has no lifecycle scripts; its main entry is the PAPI server.
- The inspected credential and configuration flows serve the package’s PAPI status display and setup behavior.
Source & flagged code
11 flaggedPackage source references child process execution.
dist/backfill-cycle-metrics.jsView on unpkg · L1014A single source file combines environment access, network access, and code or shell execution; review context before blocking.
dist/backfill-cycle-metrics.jsView on unpkg · L3974Findings
Affected versions and remediation
This report applies to @papi-ai/server@0.402.206.
See all versions of @papi-ai/server for other recorded verdicts.
- Review the evidence and your use of @papi-ai/server@0.402.206 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.