@theronap/cortex-mcp@0.9.263
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 6d ago · by lpm-firewall-aiThe package has no install lifecycle hooks, and the flagged editor and channel mutations are reached through explicit CLI commands. Its authenticated session pings send working-directory and file context to the Agnoclast service, consistent with the package’s stated purpose.
Decision evidence
public snapshot- The manifest declares a CLI entry point and no npm lifecycle hooks.
- Configuration writes run through explicit setup or install commands; the installer wires only selected editors.
- The Antigravity adapter writes a script and launch-agent plist, but does not load the agent and tells the user to run `launchctl load` to activate it.
- The generated Antigravity plist sets `RunAtLoad` to false.
- Channel configuration changes occur through the `channel stable|latest` command when an argument is supplied.
- The MCP server sends session details to the Agnoclast service as part of its session-ping functionality.
- Session pings include the working directory, repository, and working-file paths; these are user environment details sent to the service.
- Setup and install write configuration into editor settings and hooks, though only when explicitly invoked.
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@0.9.263.
See all versions of @theronap/cortex-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/cortex-mcp@0.9.263 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.