VulX Watch is answering right now. Last checked 7 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 7 min ago.
claude mcp add watch --transport http https://mcp.vulx.ai/mcp
{
"mcpServers": {
"watch": {
"url": "https://mcp.vulx.ai/mcp"
}
}
}
[mcp_servers.watch]
url = "https://mcp.vulx.ai/mcp"
{
"mcpServers": {
"watch": {
"url": "https://mcp.vulx.ai/mcp"
}
}
}
{
"mcpServers": {
"watch": {
"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 | 555 ms | 7 min ago |
Agent-ready feedback for AI-built apps — read and close UI feedback reports over MCP.
FinishKit MCP: scan GitHub repos for security vulnerabilities, deployment blockers, and quality
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.
Hiring, SEC, research papers, GitHub & Hacker News as JSON for AI agents. Pay-per-result on Apify.
Independent static verification for exact immutable public GitHub commits.
MCP server that scans your repo's dependencies for security vulnerabilities based on published CVEs.
Safety boundary for agent written GitHub PR reviews: pending and invisible, submitting is opt-in
Answers built from our own checks of this server.