@compr/opscontext-mcp@2.2.0
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-aiThis is a real agent-control and persistence capability, but it is explicitly user-invoked and not lifecycle-reachable at installation. Per policy it warrants a warning rather than a publication block.
Static reason
No blocking static signals were detected.
Trigger
User runs install-claude-hook or install-autostart.
Impact
Captures prompt text and tool-call metadata locally after user-enabled setup.
Mechanism
Claude hook captures session events to a local audit service.
AI rationale
This is a real agent-control and persistence capability, but it is explicitly user-invoked and not lifecycle-reachable at installation. Per policy it warrants a warning rather than a publication block.
Evidence
package.jsondist/cli.jsdist/install-claude-hook.jsdefaults/claude-code-hook.shdist/install-autostart.jsdist/http-server.js~/.claude/settings.json~/.claude/hooks/opscontext-emit.sh~/Library/LaunchAgents/com.opscontext.mcp.plist~/.contextengine/audit.log
Network endpoints1
127.0.0.1:7842/events
Decision evidence
public snapshotAI called this Suspicious at 91.0% confidence as Dangerous Capability with low false-positive risk.
Evidence for warning
- Explicit CLI command installs Claude Code hook entries.
- Installed hook captures prompts and tool-call previews.
- Explicit autostart command creates a per-user LaunchAgent.
Evidence against
- No preinstall, install, or postinstall lifecycle hook.
- Hook traffic targets authenticated localhost only.
- Agent configuration mutation is command-gated, not automatic.
Behavioral surface
ChildProcessCryptoDynamicRequireEnvironmentVarsFilesystemNetworkShell
HighEntropyStringsUrlStrings
Source & flagged code
5 flagged · loading sourcedist/adapters.jsView file
46}
L47: const mod = await import(moduleSpecifier);
L48: // Check for factory function
Medium
Dynamic Require
Package source references dynamic require/import behavior.
dist/adapters.jsView on unpkg · L46dist/install-autostart.jsView file
13Trigger-reachable persistence chain: manifest.bin -> dist/cli.js -> dist/install-autostart.js
L13: // forever — defeating the whole point.
L14: // FIX: To add platform support beyond macOS, branch on process.platform and
L15: // add equivalent systemd / NSSM logic. Keep `gui/$UID` and KeepAlive
...
L19: import { homedir, platform } from "os";
L20: import { execSync } from "child_process";
L21: import { createRequire } from "module";
...
L34: const __filename_esm = fileURLToPath(import.meta.url);
L35: const __dirname_esm = dirname(__filename_esm);
L36: const requireFromHere = createRequire(import.meta.url);
...
L126: <key>StandardOutPath</key>
L127: <string>${join(LOG_DIR, "mcp-stdout.log")}</string>
L128:
High
Trigger Reachable Persistence
A manifest entrypoint or package-local install chain reaches persistence behavior.
dist/install-autostart.jsView on unpkg · L13Findings
2 High6 Medium5 Low
HighTrigger Reachable External Ai Agent Control Surface Mutationdist/install-claude-hook.js
HighTrigger Reachable Persistencedist/install-autostart.js
MediumDynamic Requiredist/adapters.js
MediumNetwork
MediumEnvironment Vars
MediumInstall Persistencedist/install-autostart.js
MediumShips Build Helperdefaults/claude-code-hook.sh
MediumStructural Risk Force Deep Review
LowNon Install Lifecycle Scripts
LowScripts Present
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings
Affected versions and remediation
This report applies to @compr/opscontext-mcp@2.2.0.
See all versions of @compr/opscontext-mcp for other recorded verdicts.
- Review the evidence and your use of @compr/opscontext-mcp@2.2.0 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.