@theronap/cortex-mcp@0.9.279
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 hook, and the flagged credential flow sends account proof with a user token to the Cortex confidential-session endpoint for seat authorization. The persistence hint describes artifacts created by an editor wiring operation that are not activated automatically.
Decision evidence
public snapshot- The manifest defines a CLI and no lifecycle scripts; its stated purpose is connecting an AI assistant to Cortex.
- The flagged confidential-session flow sends account proof with a user token to the confidential agent-session endpoint on the configured Cortex service.
- The server checks for confidential seats and account proof as part of opening a named confidential brain; the package describes approval and account dedication requirements.
- Antigravity wiring writes a shell script and launch-agent plist, but says a person must run launchctl load to activate the watcher.
- The service’s canonical base URL is agnoclast.com.
- The apparent api.openai.com credential match is an OpenAI ID-token claim used to identify the signed-in account, not a request sending that token to OpenAI.
- The channel configuration is written by an explicit channel command, and the setup/install branches are explicit CLI commands.
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@0.9.279.
See all versions of @theronap/cortex-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/cortex-mcp@0.9.279 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.