# Guardian Engine MCP server

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

## Links
- Registry page: https://www.getdrio.com/mcp/dev-kaimeilabs-guardian-engine
- Repository: https://github.com/kaimeilabs/guardian-api-docs

## Install
- Endpoint: https://api.kaimeilabs.dev/mcp
- Auth: Not captured

## Setup notes
- Remote endpoint: https://api.kaimeilabs.dev/mcp

## Tools
- 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; more than 5 WARNINGs also fail. There is no score in the
response (ADR-013): gate on `verdict` and explain failures from `findings`.

**Field audience**: `issue` is a machine-readable code for programmatic handling — never
show it to end users. Use `title` and `suggested_correction` as the user-facing fields.

Returns a formatted text report or structured JSON (response_format="json").
In Oracle Mode (default), proprietary data is protected — exact values are replaced
with directional hints. Endpoint: https://api.kaimeilabs.dev/mcp
- 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 LLM is used — the repair is a deterministic function of the
candidate recipe and the master ruleset.

Findings that need recipe-authoring judgement — adding a whole cooking
phase, rewriting step instructions, ingredient-ratio rebalancing — are not
auto-applied; they are returned under `patches_skipped`. Allergen findings
are never auto-fixed. The response reports the verdict before and after so
the caller can see exactly what was resolved.

Note: `verdict_after` may still be FAILED when structural changes (e.g.
adding a cooking step, rebalancing ingredient ratios) are needed. These
require recipe-authoring judgement and are returned under `patches_skipped`.
Callers should NOT assume a fixed recipe will pass verification. Endpoint: https://api.kaimeilabs.dev/mcp
- list_dishes - List all available master dishes with rich metadata.

Returns:
    Dictionary with `schema_version` and a `dishes` list. Each dish includes
    slug, title, cuisine, region, aliases, and complexity. Endpoint: https://api.kaimeilabs.dev/mcp
- 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 by default (ADR-009 / ADR-010): exact temperatures, timings,
and EU FIC 1169/2011 allergen codes are returned verbatim, never obfuscated. No score is
included (ADR-013) — this is reference data, not a verdict.

Returns ingredients, steps (technique/temperature/timing/medium), and the EU FIC allergens
derived from the required ingredients. Unknown dishes return a structured UNKNOWN_DISH error. Endpoint: https://api.kaimeilabs.dev/mcp
- 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.

Use check_all_eu_allergens=True for food labelling (detect all allergens).
Use restrictions=['dairy', 'gluten'] to check for specific user allergies. Endpoint: https://api.kaimeilabs.dev/mcp
- 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 justification — never a
vague paraphrase. Endpoint: https://api.kaimeilabs.dev/mcp

## Resources
Not captured

## Prompts
- verify_recipe_prompt - Provides instructions and a template for an AI agent to verify a recipe.

Args:
    dish: The name of the dish to verify (e.g. 'carbonara', 'rendang'). Arguments: dish

## Metadata
- Owner: dev.kaimeilabs
- Version: 1.0.0
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Feb 27, 2026
- Source: https://registry.modelcontextprotocol.io