@theronap/cortex-mcp@0.9.262
Renamed to @theronap/agnoclast-mcp — use that. Existing installs switch themselves to the new name on next start.
Connect your AI assistant to Cortex — your org's projects, activity, gaps, and directives, scoped to you.
AI Security Review
scanned 12d ago · by lpm-firewall-aiThe manifest defines no install lifecycle hooks, and the flagged configuration and watcher writes are reached through explicit CLI setup or install commands. The inspected source supports normal product behavior, with no concrete attack established.
Decision evidence
public snapshot- package.json has no install lifecycle hooks and declares the MCP SDK and Zod as runtime dependencies.
- The entrypoint invokes setup or editor wiring only for explicit CLI commands; the inspected Codex and Cursor configuration writes are inside their wiring functions.
- Channel settings change only when the command receives a valid channel argument; without one, it reports status.
- Antigravity wiring writes a watcher plist with RunAtLoad disabled and does not load it automatically.
- The inspected support modules perform session summarization, graph synchronization, proposal review and changed-file tracking; the dependency entrypoints expose library exports.
- The configured canonical service endpoint is agnoclast.com.
Source & flagged code
6 flaggedPackage source references weak cryptographic algorithms.
lib/capture.mjsView on unpkg · L1Findings
Affected versions and remediation
This report applies to @theronap/cortex-mcp@0.9.262.
See all versions of @theronap/cortex-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/cortex-mcp@0.9.262 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.