MCP gateway proxy for varied backends
- capability exposure inferred + 35
- tool safety inferred + 5
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 44s ago · see ecosystem CVEs →
No known CVEs for this server.
- medium dangerous code
dynamic exec: eval()/exec()
- low dangerous code
env-secret-flows-to-network-py: An environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a key, call
analyzed commit b0bfb8a · analyzer v32 · 1h ago
danger signals2
- dynamic code execution eval()/exec() rShetty-relay-b0bfb8a/gateway/server.py :3141
exec(fn_code, local_ns, local_ns) - over-broad OAuth scope delete_repo rShetty-relay-b0bfb8a/tests/test_patroclus.py :111
resource="github/delete_repo",
[](https://mcpobservatory.com/servers/github:rShetty/relay/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 rShetty.