Build-time security scanning for MCP servers — static + GPT-reviewed + Docker-verified findings mapped to the OWASP Agentic Top 10, with SARIF/GitHub Action support.
- capability exposure inferred + 35
- recent drift inferred + 12
- tool safety inferred + 5
- trust mitigators mixed − 3
inferred mixed
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.
graded 1m ago · see ecosystem CVEs →
- B · 32 → C · 49
No known CVEs for this server.
- medium dangerous code
dynamic exec: eval()/exec()
analyzed commit e717e95 · analyzer v28 · 1d ago
skills & prompt files 1
- agent-rules BashaarJavaid-MCP-Sentinel-e717e95/AGENTS.md
danger signals2
- dynamic code execution eval()/exec() BashaarJavaid-MCP-Sentinel-e717e95/tests/fixtures/gpt_review_eval/server.py :17
return eval(expression) - dynamic code execution eval()/exec() BashaarJavaid-MCP-Sentinel-e717e95/tests/fixtures/vulnerable_server/server.py :27
return eval(expression)
- recent drift +12 capability drift →
[](https://mcpobservatory.com/servers/github:BashaarJavaid/MCP-Sentinel/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 BashaarJavaid.