@compr/opscontext-mcp@2.5.4
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 explicit persistence and Claude Code hook setup with prompt and tool-event collection, so it warrants a warning. Direct inspection found no install-time execution or evidence that these capabilities are activated without the user's named CLI command.
Decision evidence
public snapshot- An explicit CLI command installs a persistent macOS LaunchAgent.
- An explicit CLI command copies a Claude Code hook and adds hook entries that capture prompts and tool activity.
- The bundled hook posts captured events to a configurable local endpoint.
- package.json has no preinstall, install, or postinstall lifecycle hook.
- The persistence and Claude hook modules are reached only by named CLI commands.
- The hook defaults to localhost, and the observed remote requests are package-aligned licensing and community-rule services.
Source & flagged code
6 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@2.5.4.
See all versions of @compr/opscontext-mcp for other recorded verdicts.
- Review the evidence and your use of @compr/opscontext-mcp@2.5.4 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.