Loading…
Deterministic recipe verification for AI agents. Catches hallucinated temperatures, missing techniques, wrong ingredients, and impossible cooking steps — then suggests one-click fixes. Covers 161+ dishes across 5 cuisines. Also checks EU allergen compliance (all 14 Annex II groups), verifies dietary claims (vegan, halal, kosher, gluten-free), and flags safety issues. Verify against Guardian's built-in master specs or your own house recipe. Same input → same verdict, every time. No API key required.
Review before connecting
The server requires authorization, so only its authentication surface was graded. Review that posture — and the tools it exposes once authenticated — before connecting.
Scanned 3 days ago
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The Guardian MCP server requires authorization, so its tools were not enumerated during the automated scan. Its published description reads: "Deterministic recipe verification for AI agents". It communicates over Streamable HTTP, and requires authorization before its tools can be called. MCPGrade currently rates Guardian N — the server requires authorization, so only its authentication surface was graded and the tool surface could not be assessed without a valid token. Its most notable findings include "Open dynamic client registration" and "PKCE S256 enforced". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check Guardian's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add Guardian to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://server.smithery.ai/kaimeilabs/guardian-engine/mcpStreamable HTTP transport. It requires authorization before its tools can be called. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
Unauthenticated DCR lets anyone register a client — an abuse and confused-deputy surface.
RecommendationPrefer CIMD; if DCR is offered, gate or rate-limit it.
The authorization server enforces PKCE with S256.
Supports CIMD — verifiable client identity without open DCR.
Zoom integration for meetings, chat, docs, recordings, and AI-generated collaboration content.
Zoom integration for meetings, chat, docs, recordings, and AI-generated collaboration content.
Zoom integration for meetings, chat, docs, recordings, and AI-generated collaboration content.
Creates, updates, assigns, and synchronizes Zoom task workflows for AI agents.
Provides meeting search, recordings, transcripts, summaries, and meeting assets for Zoom Meetings.