The autonomous security agent for your AI stack — finds the vulns in your MCP servers & agent tools AND writes the fixes, on a local model.
- capability exposure inferred + 10
- tool safety inferred + 12
inferred
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
grade last moved 3d ago · see ecosystem CVEs →
- B · 34 → B · 22
- A · 10 → B · 34
- A · 0 → A · 10
No known CVEs for this server.
- high dangerous code
committed secret: Stripe live key
analyzed commit 92fa7b3 · analyzer v33 · 2w ago
danger signals2
- committed secret Stripe live key cognis-digital-shrike-92fa7b3/demos/vulnerable-stack/files-mcp.json :5
sk_liv…(28 chars, redacted) - committed secret Stripe live key cognis-digital-shrike-92fa7b3/demos/vulnerable-stack/github-mcp.json :5
sk_liv…(28 chars, redacted)
[](https://mcpobservatory.com/servers/github:cognis-digital/shrike/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of cognis-digital.