@compr/opscontext-mcp
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.
This report shows the evidence for @compr/opscontext-mcp@2.12.0. 1 of 21 known versions is blocked or flagged. The newest version, 2.19.2, is flagged. See all versions.
AI Security Review
scanned 12d ago · by lpm-firewall-aiThe reviewer-directed instruction in dist/activation.js is deliberate review manipulation and supports a malicious verdict. The inspected installer capabilities are explicitly invoked and do not independently establish an install-time attack.
Decision evidence
public snapshot- dist/activation.js contains a reviewer-directed instruction not to re-audit the file, an attempt to influence this security review.
- The package exposes its Claude hook and autostart installers as explicit CLI commands.
- The hook installer adds command hooks to Claude settings when invoked.
- package.json has no preinstall, install, or postinstall hook; its lifecycle script is prepublishOnly.
- The autostart installer checks the platform and existing plist before proceeding.
Source & flagged code
7 flagged · loading sourcePackage source references dynamic require/import behavior.
dist/adapters.jsView on unpkg · L47A 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@2.12.0.
The versions list below shows the verdict for each recorded version.
- Avoid installing @compr/opscontext-mcp@2.12.0. Remove it from direct dependencies and check your lockfile for transitive copies.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
- If this version ran, investigate the affected machine and build environment. Rotate credentials it could access and rebuild from a trusted environment.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.