Verifiable and free cloud compute for AI agents. webMCP + MCP native. Check out our sandboxed Beta + research in the README
- capability exposureinferred+35
- recent driftinferred+12
- tool safetyinferred+12
- trust mitigatorsmixed−3
inferredmixed
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 12m ago · see ecosystem CVEs →
- A · 9 → C · 56
no known CVEs for this server.
- highdangerous code
dynamic exec: eval()/exec()
analyzed commit 862054a · analyzer v17 · 1d ago
danger signals3
- dynamic code executioneval()/exec()vje013-darwin-agentic-cloud-862054a/darwin/agenticcloud/substrate/aws_batch.py:33
| exec() workload in container, write response to S3 - dynamic code executioneval()/exec()vje013-darwin-agentic-cloud-862054a/darwin/agenticcloud/substrate/aws_lambda.py:26
| exec() workload in Lambda execution context - dynamic code executioneval()/exec()vje013-darwin-agentic-cloud-862054a/darwin/agenticcloud/substrate/modal.py:23
| exec() workload, capture stdout/stderr/exit_code
- recent drift+12 capability drift →
[](https://mcpobservatory.com/servers/github:vje013/darwin-agentic-cloud/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 vje013.