Offensive MCP server auditor — detects tool poisoning, credential leaks, RCE vectors, SSRF, session hijacking, and supply chain vulnerabilities across stdio, HTTP, and SSE transports.
- capability exposureinferred+22
- recent driftinferred+12
- tool safetyinferred+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.
graded 5m ago · see ecosystem CVEs →
- A · 0 → C · 46
no known CVEs for this server.
- highdangerous code
dynamic exec: eval()
analyzed commit 4feccf8 · analyzer v17 · 3h ago
danger signals2
- dynamic code executioneval()sahiloj-MCPScan-4feccf8/src/checks/overprivileged.ts:21
'code-eval': /\b(?:eval(?:uate)?|interpret|execut(?:e|ing)\s+code|run\s+(?:code|script)|sandbox|repl|compile)\b/i, - dynamic code executioneval()sahiloj-MCPScan-4feccf8/src/checks/rce-vectors.ts:16
/eval(?:uate)?s?\s+(?:arbitrary\s+)?(?:code|expression|javascript|python|ruby)/i,
- recent drift+12 capability drift →
[](https://mcpobservatory.com/servers/github:sahiloj/MCPScan/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 sahiloj.