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.
noviqtechnologies/vexa-agentwall is an MCP server distributed on github, maintained by noviqtechnologies, tracked here since August 2026. It has shipped 30 releases. Its composite risk grade is C — an inferred review prompt computed from observed signals, not a verdict.
Reading the source raised one review prompt — dangerous code — each a pattern worth a human look rather than a finding of fault.
full security breakdown →No tools recorded for this server yet.
06-15 00:00 07-29 00:00 now
| version | date | src |
|---|---|---|
| v1.0.32 | 2026-08-12 | github |
| v1.0.31 | 2026-08-11 | github |
| v1.0.30 | 2026-08-11 | github |
| v1.0.29 | 2026-08-11 | github |
| v1.0.28 | 2026-08-10 | github |
| v1.0.27 | 2026-08-10 | github |
| v1.0.26 | 2026-08-10 | github |
| v1.0.25 | 2026-08-09 | github |
| v1.0.24 | 2026-08-09 | github |
| v1.0.23 | 2026-08-07 | github |