Vexa AgentWall is a full egress proxy and security gateway for AI agents operating over MCP, HTTP, HTTPS, and WebSocket connections. It provides organizations with a default-deny control plane to intercept, sandbox, audit, and actively block unauthorized agent tool calls and data exfiltration attempts.
This grade was produced by analyzer v30 , 3 version s behind the one running now. Detectors added since have not been applied here, so it is not directly comparable with a server analyzed at the current version. A re-scan is queued.
- capability exposure inferred + 10
- recent drift inferred + 12
- tool safety inferred + 12
- 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.
graded 6m ago · see ecosystem CVEs →
No known CVEs for this server.
- high dangerous code
committed secret: Google API key, AWS access key id, Anthropic key, private key
analyzed commit 0b78762 · analyzer v30 · 2w ago
danger signals7
- committed secret Google API key noviqtechnologies-vexa-agentwall-0b78762/agentwall-policy.yaml :61
AIzaSy…(39 chars, redacted) - committed secret AWS access key id noviqtechnologies-vexa-agentwall-0b78762/control-plane/proto/src/tests.rs :159
AKIAIO…(20 chars, redacted) - committed secret Anthropic key noviqtechnologies-vexa-agentwall-0b78762/src/policy/dlp.rs :592
sk-ant…(44 chars, redacted) - committed secret private key noviqtechnologies-vexa-agentwall-0b78762/src/policy/identity.rs :281
PEM private key block (redacted) - committed secret Anthropic key noviqtechnologies-vexa-agentwall-0b78762/src/policy/response_scanner.rs :497
sk-ant…(33 chars, redacted) - committed secret private key noviqtechnologies-vexa-agentwall-0b78762/test-tools/dogfood/setup-windows.ps1 :24
PEM private key block (redacted) - committed secret private key noviqtechnologies-vexa-agentwall-0b78762/tests/unit/oidc_tests.rs :13
PEM private key block (redacted)
- recent drift +12 capability drift →
[](https://mcpobservatory.com/servers/github:noviqtechnologies/vexa-agentwall/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 noviqtechnologies.