@compr/opscontext-mcp@2.9.1
OpsContext for AI Agents — read-only fleet visibility (PM2/nginx/Docker/git/cron) + tamper-evident audit log + policy-as-code hooks. The ops + compliance layer Claude Code can't grow natively.
AI Security Review
scanned 12d ago · by lpm-firewall-aiThe manifest has no install-time lifecycle hook, and the flagged configuration and persistence changes are reached through explicit CLI installer commands. The inspected source supports a clean verdict; scanner labels alone do not establish malicious behavior.
Decision evidence
public snapshot- package.json defines a prepublish-only build hook but no preinstall, install, or postinstall hook.
- The flagged agent-related code includes project-file checks and package-owned skill installation behavior.
- The command-line entrypoint exposes the hook and autostart installers as explicit commands.
- Hook installation writes OpsContext hook entries into Claude settings when its installer command runs.
- Autostart is installed through an explicit command and is limited to a user-level macOS launch agent.
Source & flagged code
7 flagged · loading sourcePackage source references dynamic require/import behavior.
dist/adapters.jsView on unpkg · L46A manifest entrypoint or package-local install chain reaches persistence behavior.
dist/install-autostart.jsView on unpkg · L13Findings
Affected versions and remediation
This report applies to @compr/opscontext-mcp@2.9.1.
See all versions of @compr/opscontext-mcp for other recorded verdicts.
- Review the evidence and your use of @compr/opscontext-mcp@2.9.1 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.