Audit all locally configured MCP servers for permission risks, prompt injection threats, and schema drift
- capability exposure inferred + 35
- recent drift inferred + 20
- tool safety inferred + 12
- trust mitigators mixed − 17
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.
grade last moved 3d ago · see ecosystem CVEs →
- C · 56 → C · 50
- D · 64 → C · 56
- C · 56 → D · 64
- B · 32 → C · 56
- A · 0 → B · 32
No known CVEs for this server.
- high dangerous code
dynamic exec: unsafe yaml.load()
analyzed commit 3dc9aad · analyzer v33 · 3d ago
skills & prompt files 3
danger signals2
- dynamic code execution unsafe yaml.load() saagpatel-MCPAudit-3dc9aad/src/mcp_audit/pinning.py :457
raw: Any = yaml.load(data.decode("utf-8"), Loader=_NoAliasSafeLoader) # noqa: S506 - loader subclasses SafeLoader - suspicious endpoint 169.254.169.254 (cloud metadata) saagpatel-MCPAudit-3dc9aad/tests/test_artifact_verify.py :72
assert not is_allowed_artifact_url("https://169.254.169.254/latest/meta-data/")
- recent drift +20 capability drift →
[](https://mcpobservatory.com/servers/github:saagpatel/MCPAudit/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 saagpatel.