@compr/opscontext-mcp@2.5.2
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 2mo ago · by lpm-firewall-aiThe package contains a real remote-code delivery path and sensitive AI-agent instrumentation. Its persistence and hook setup are explicit user commands rather than npm lifecycle behavior, so the source does not establish malicious install-time conduct.
Decision evidence
public snapshot- Activation downloads encrypted JavaScript, decrypts it, writes it under the user home directory, and dynamically imports it.
- An explicit command installs hooks that capture Claude Code prompts and tool-call details.
- An explicit command creates a persistent macOS LaunchAgent for the package server.
- package.json has no preinstall, install, or postinstall hook.
- The Claude hook and autostart changes require explicit CLI commands.
- The hook posts to a localhost endpoint rather than an external endpoint.
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@2.5.2.
See all versions of @compr/opscontext-mcp for other recorded verdicts.
- Review the evidence and your use of @compr/opscontext-mcp@2.5.2 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.