agent-sec MCP: what works in Claude, ChatGPT, Cursor, and Grok Bot
Zero-install security baseline for AI coding agents — OWASP/CWE-cited rules over MCP.
Registry name: ai.kernora/agent-sec (v0.1.0) | GitHub stars
Status grid
| App | Status | Date tested |
|---|---|---|
| Claude | Untested | Not yet tested |
| ChatGPT | Untested | Not yet tested |
| Cursor | Untested | Not yet tested |
| Grok Bot | Untested | Not yet tested |
| MCP Inspector (reference client) | Untested | Not yet tested |
| MCP TypeScript SDK (reference client) | Untested | Not yet tested |
Hands-on test results
No hands-on tests yet. We do not publish results until we have actually tested.
Automated handshake
Works HTTP 200, 596 ms, checked Fri, 16 Oct 2026 17:08:28 GMT
Gotchas
None recorded yet. Gotchas come only from hands-on tests.
Request a hands-on test of agent-sec
Get the badge
Maintain agent-sec or write about it? Show its live ConnectorReport status in your README or docs.
Markdown (README, docs)
[](https://connectorreport.com/c/ai-kernora-agent-sec?utm_source=badge&utm_medium=embed&utm_campaign=ai-kernora-agent-sec)
HTML
<a href="https://connectorreport.com/c/ai-kernora-agent-sec?utm_source=badge&utm_medium=embed&utm_campaign=ai-kernora-agent-sec"><img src="https://connectorreport.com/badge/ai-kernora-agent-sec.svg" alt="agent-sec MCP status on ConnectorReport"/></a>
The badge updates on its own after every retest. How badges work