Epicure
    KitchenCollectionMethodMCP
    Enter kitchen
    Epicure for AI agents

    Give your agenta palate.

    Connect any MCP client to Epicure's read-only ingredient intelligence through one public endpoint.

    Try a live toolExplore all tools

    Public MCP

    Checking live service

    Remote endpoint

    https://epicure-mcp.kaikaku.ai/mcp
    Transport
    Streamable HTTP
    Access
    Public
    Tools
    Checking

    Connection object

    {
      "name": "Epicure",
      "url": "https://epicure-mcp.kaikaku.ai/mcp"
    }

    Read-only tools
    13
    Ingredients
    1,790
    Model dimensions
    300
    Recipe corpus
    4.14M
    A real MCP response

    Test a pairing before you connect.

    This form opens a live MCP session and calls the same pairing tool available to your agent.

    Call pairing_score

    Ingredient names are resolved deterministically against the live atlas.

    Run the live tool to see how the model positions this relationship inside its corpus.

    A measured taste signal appears here.

    The complete tool surface

    From an ingredient question to a structured answer.

    Every operation is deterministic, idempotent, and read-only. No recipe or ingredient data is changed.

    Explore

    Find useful relationships and place ingredients inside the atlas.

    find_pairings
    Build a cluster and bridge graph around one or more ingredients.
    neighbors
    Return the nearest ingredients in the 300-dimensional model.
    where_on_atlas
    Locate an ingredient on the UMAP atlas with nearby peers.
    closest_mode
    Identify the named flavour region an ingredient occupies.

    Measure

    Quantify affinity, cuisine direction, and learned flavour structure.

    pairing_score
    Measure cosine affinity between two ingredients with a corpus percentile.
    compare_on_axis
    Compare two ingredients on a verified culinary axis.
    cultural_profile
    Measure an ingredient against eight cuisine directions.
    flavour_correlations
    Inspect correlations between the model's flavour axes.
    ingredient_on_factor
    Project an ingredient onto a residual flavour factor.

    Transform

    Navigate toward a target while preserving a clear culinary starting point.

    morph
    Rotate an ingredient toward another ingredient, mode, or direction.
    pareto_navigate
    Balance closeness to a seed against a named flavour pole.
    list_targets
    Discover valid axes, modes, and directions before transforming.
    list_factors
    Inspect the available residual flavour factors and their poles.

    How the connection runs

    Public at the edge. Private at the origin.

    Cloudflare carries each request to Epicure's self-hosted compute without exposing an origin port.

    1. Your AI client

      Sends a standard MCP request from its reasoning loop.

    2. Cloudflare edge

      Terminates TLS and carries the request through the private tunnel.

    3. Epicure MCP

      Runs one of thirteen deterministic, read-only tools on self-hosted compute.

    4. Flavour atlas

      Returns a structured result from the 300-dimensional ingredient model.

    The website, API, and MCP remain separate services behind the same local cluster and Cloudflare tunnel.

    Explore the kitchen

    Epicure by Kaikaku

    Cook beyond the obvious.

    KitchenRecipe collectionThe methodMCP for agents
    Kaikaku AI

    Protected by Cloudflare Turnstile. Cloudflare's Privacy Policy and Terms apply.

    Pinned AI models run through OpenRouter with provider data collection disabled. Read OpenRouter's Privacy Policy.

    PrivacySupportGitHubXLinkedInInstagram© 2026 Epicure