The operating system that AI workflows trust. Structure messy inputs. Establish identity. Track provenance. Build the durable data layer your AI workflows need to be trusted, reusable, and auditable.
- capability exposure inferred + 35
- tool safety inferred + 14
- 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.
grade last moved 10h ago · see ecosystem CVEs →
- C · 58 → C · 46
- B · 32 → C · 58
- A · 0 → B · 32
No known CVEs for this server.
- medium dangerous code
dynamic exec: __import__()
- medium toxic flow (lethal trifecta)
lethal trifecta reachable across this server's tools: private-data access + untrusted-content ingestion + network exfil
- low exfiltration combo rotate_api_key
single tool reads + sends: net, secrets
- low exfiltration combo
sensitive read and network capabilities split across this server's tools
analyzed commit b97fbfe · analyzer v33 · 3d ago
danger signals1
- dynamic code execution __import__() Agience-agience-core-b97fbfe/docs/api/build_openapi.py :80
mod = __import__(module, fromlist=["app"])
[](https://mcpobservatory.com/servers/github:Agience/agience-core/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 Agience.