VulX Watch is answering right now. Last checked 5 min ago. Last commit 1 Sep 2026.
Independent security review for AI-built apps. Watch a GitHub repo. Never a patch.
Today is the operative word: we check VulX Watch every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 5 min ago.
claude mcp add watch --transport http https://mcp.vulx.ai/mcp
https://mcp.vulx.ai/mcp
[mcp_servers.watch]
url = "https://mcp.vulx.ai/mcp"
{
"mcpServers": {
"watch": {
"url": "https://mcp.vulx.ai/mcp"
}
}
}
{
"servers": {
"watch": {
"type": "http",
"url": "https://mcp.vulx.ai/mcp"
}
}
}
This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://mcp.vulx.ai/mcp | streamable-http | sign-in | 333 ms | 5 min ago |
Agent-ready feedback for AI-built apps — read and close UI feedback reports over MCP.
Independent second opinion on any AI answer: inaccuracies, gaps, and a scored report card.
FinishKit MCP: scan GitHub repos for security vulnerabilities, deployment blockers, and quality
Offline, rule-based security checks for your repo, dependencies, AI agent config and local app.
Ship, discover and review vibe-coded projects on Shipyard, the invite-only feed for AI-built apps.
Audit GitHub repos for malicious and supply-chain code before you depend on them.
Free security scan for AI-written GitHub repos: leaked keys, .env, eval, SQLi, CORS.
Hiring, SEC, research papers, GitHub & Hacker News as JSON for AI agents. Pay-per-result on Apify.
Answers built from our own checks of this server.