Categories › AI & Agents › Thinking, planning & prompt tools
Deterministic recipe verification engine — validates AI-generated recipes against master SOPs.
Remote server: your requests and data go to api.kaimeilabs.dev. Claude Code: claude mcp add --transport http guardian-engine https://api.kaimeilabs.dev/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
verify_recipe — Verify a candidate recipe against a Guardian master recipe. Uses deterministic graph-based verification to check technique, temperature, timfix_recipe — Deterministically repair a candidate recipe against a Guardian master. Verifies the candidate, applies every machine-actionable correction tlist_dishes — List all available master dishes with rich metadata. This is a browse/discovery step, not the verification itself — after picking a dish, caget_master — Return the canonical master recipe for a dish (read-only, no LLM). Enables compare-then-verify agentic loops: fetch the master, diff it agaicheck_safety — Run master-independent safety checks on a candidate recipe. Works for ANY recipe — no dish resolution, no master SOP required. Checks poultrcheck_allergens — Check ingredients for EU FIC 1169/2011 allergen compliance. Returns a detailed audit trace mapping each ingredient to its EU Annex II allergverify_dietary_claim — Verify that a recipe satisfies a dietary claim (vegan, halal, gluten-free, ...). Reuses the existing allergen-detection logic plus a curatedNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.