ai-gantry is a stupid-simple agent runtime: one static Go binary that runs one persona with one model and whatever MCP tool binaries you mount next to it. Built for distroless/static containers, configured entirely by env + mounts. No dashboard, no config UI, no open ports — ever.
- trust mitigators mixed − 3
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 3m ago · see ecosystem CVEs →
No known CVEs for this server.
No tool-safety findings — heuristic detectors run on the compute-risk cadence; a finding appears when a tool trips a rule.
[](https://mcpobservatory.com/servers/github:shotah/ai-gantry/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 shotah.