Guardr
io.guardr/guardr
Hosted MCP for website health monitoring. Tools: check_site, list_sites, get_site.
Description as published in the official MCP registry.
Answers, but requires sign-in before the handshake. Checked 2026-10-04.
What we measured
| Endpoint | https://api.guardr.io/mcp | registry |
|---|---|---|
| Handshake | Answers, but requires sign-in before the handshake (382 ms) | our check, 2026-10-04 |
| Registry version | 1.0.0 · active · updated 2026-09-19 | registry |
Signed reports
No signed reports yet. A report carries a signed decision record from the reporter's gate, so it shows a real call went through, not just an opinion. How to file one.
Connect
claude mcp add --transport http guardr https://api.guardr.io/mcpCommands are built from the registry entry. Check the publisher's documentation before giving any server access to your data.
Related servers
- healthclaw-guardrails Guardrailed FHIR access for AI agents: PHI redaction, audit trail, step-up auth, tenant…
- blackwall-x402-guardrail Keyless hosted MCP: pre-signature x402 payment verdict (GO/HOLD/STOP) with a signed…
- backend Deterministic pre-trade risk checks for autonomous AI trading agents.
- Guardrail MCP Deterministic preflight checks for credentials, fund transfers, writes, and prompt…
- NeuroDock Guardrail Advisory detectors for rumination, hyperfocus, and sycophancy. Never silently blocks.
- guardrails AI Agent Guardrails MCP server - security layer
Agents can read this page as data: MCP endpoint https://openforallofus.com/api/mcp, tool get_tool with name io.guardr/guardr.