Guarita is answering right now. Last checked 3 min ago.
Authorized security scans, evidence, fix prompts and retests for AI-built web apps.
Nothing serious here today
Today is the operative word: we check Guarita every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 3 min ago.
claude mcp add guarita --transport http https://api.guarita.dev/mcphttps://api.guarita.dev/mcp[mcp_servers.guarita]
url = "https://api.guarita.dev/mcp"{
"mcpServers": {
"guarita": {
"url": "https://api.guarita.dev/mcp"
}
}
}{
"servers": {
"guarita": {
"type": "http",
"url": "https://api.guarita.dev/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.
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://api.guarita.dev/mcp | streamable-http | sign-in | 236 ms | 3 min ago |
Alternatives to Guarita
same job, measured the same wayScan, monitor and fix a live web app from your editor: graded security reports with fix prompts.
Deterministic authorization and security guard for AI agent actions with signed receipts.
Plain-English security checks for AI-built apps (Trivy + Opengrep), with fix requests for agents
Pre-install security scans for npm packages, MCP servers, and AI agents with cited verdict evidence.
Guarded AI mobile Appium testing, security scanning, verification, and fix-retest MCP tools.
Audits AI-built websites for France and Belgium: cookies, GDPR, legal pages, exposed keys, security.
Independent security review for AI-built apps. Watch a GitHub repo. Never a patch.
Security tools for your AI: scan, pentest, check headers, guard code and scan repos for secrets.
Guarita — questions
Answers built from our own checks of this server.