@theronap/cortex-mcp@0.9.234
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 20d ago · by lpm-firewall-aiThe runtime permits a user-configured custom host to receive the service token, which creates a conditional credential exposure risk. The package has no npm install hook, and the flagged agent setup behavior is separately invoked or requires manual activation, so this supports a warning rather than a block.
Decision evidence
public snapshot- The manifest defines a CLI entrypoint and only release, promote, and rollback scripts; it has no npm install lifecycle hook.
- The token resolver reads the token from the environment. CORTEX_URL defaults to the Agnoclast host, but a custom domain is accepted without an allowlist.
- The MCP server sends its bearer token to BASE in an automatic session ping at startup and every minute; BASE comes from CORTEX_URL.
- The flagged editor and skill code concerns scoped setup or removal behavior. Antigravity writes launcher files, but its source requires a separate manual load command to activate the watcher.
- The package does not silently install these integrations during npm installation; setup, install, and uninstall are separate CLI commands.
- The credential exposure requires configuring CORTEX_URL to a custom domain; the default destination is the package's Agnoclast service. The source does not establish hidden transfer or malicious intent.
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@0.9.234.
See all versions of @theronap/cortex-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/cortex-mcp@0.9.234 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.