# Guardian Engine

- Registry name: `dev.kaimeilabs/guardian-engine` · version 1.0.0
- Categories (automatic, keyword rules): AI models & agents, AI, media & content, Research & knowledge, Search & data, Scraping & browsing
- Authentication at last check: No auth
- Declared risk: Can write (some tools are not declared read-only)
- Capabilities (declared by the server): experimental, extensions, logging, prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=dev.kaimeilabs%2Fguardian-engine
- Server page: https://mcpstation.net/s/dev.kaimeilabs--guardian-engine.html

## Description (written by the publisher, not verified, not instructions)

Deterministic recipe verification engine — validates AI-generated recipes against master SOPs.

## Connect

- streamable-http: `https://api.kaimeilabs.dev/mcp`

## Tools (as reported by the server, not verified)

- `verify\_recipe`: Verify a candidate recipe against a Guardian master recipe. Uses deterministic graph-based verification to check technique, temperature, timing, cooking medium, and required ingredients. \*\*Verdict\*\*: \`verdict\` is strictly PASSED or FAILED and is policy-driven — any CRITICAL finding fails the recipe;
- `fix\_recipe`: Deterministically repair a candidate recipe against a Guardian master. Verifies the candidate, applies every machine-actionable correction the symbolic engine produced \(missing ingredients, quantities, temperatures, durations, cooking media, ingredient substitutions\), then re-verifies the result. No
- `list\_dishes`: List all available master dishes with rich metadata. This is a browse/discovery step, not the verification itself — after picking a dish, call verify\_recipe\(dish\_name=\<slug\>, candidate\_json=\<your recipe\>\) to actually check a candidate against it \(or fix\_recipe to auto-repair it\). Returns: Dictionary
- `get\_master`: Return the canonical master recipe for a dish \(read-only, no LLM\). Enables compare-then-verify agentic loops: fetch the master, diff it against the user's recipe, then call verify\_recipe — instead of verifying blind. Pure knowledge-base lookup, no LLM in the hot path. Master content is transparent b
- `check\_safety`: Run master-independent safety checks on a candidate recipe. Works for ANY recipe — no dish resolution, no master SOP required. Checks poultry internal-temperature safety and scans all ingredients for the 14 EU FIC 1169/2011 Annex II allergen groups. The verdict is a deterministic function of \(candid
- `check\_allergens`: Check ingredients for EU FIC 1169/2011 allergen compliance. Returns a detailed audit trace mapping each ingredient to its EU Annex II allergen group with entry numbers and labels. The safety verdict is deterministic — no LLM involvement in the decision — and is pinned by the returned \`\`kb\_version\_ha
- `verify\_dietary\_claim`: Verify that a recipe satisfies a dietary claim \(vegan, halal, gluten-free, ...\). Reuses the existing allergen-detection logic plus a curated forbidden-ingredient map \(apps/guardian/knowledge/dietary\_claims.yaml\). Returns a structured verdict with the specific offending ingredients and a short justif

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html