Cross-cuisine dish equivalence with shared-ingredient evidence: 1,956 dishes, 26 cuisines.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Compare two dishes ingredient by ingredient: shared items, what is unique to each, a match score, and - for the pairs that have one (nearly 900) - an editorial comparison paragraph in the requested language. Works for any two dishes in the corpus, whether or not they are an edge in the equivalence graph.
First dish: slug or name.
Second dish: slug or name.
Language for titles, ingredient names and URLs.
Compare two dishes ingredient by ingredient: shared items, what is unique to each, a match score, and - for the pairs that have one (nearly 900) - an editorial comparison paragraph in the requested language. Works for any two dishes in the corpus, whether or not they are an edge in the equivalence graph.
| Argument | Type | Description |
|---|---|---|
| a* | string | First dish: slug or name. |
| b* | string | Second dish: slug or name. |
| lang | string | Language for titles, ingredient names and URLs. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"a",
"b"
],
"properties": {
"a": {
"type": "string",
"minLength": 2,
"description": "First dish: slug or name."
},
"b": {
"type": "string",
"minLength": 2,
"description": "Second dish: slug or name."
},
"lang": {
"enum": [
"en",
"tr",
"de",
"fr",
"es",
"it",
"el"
],
"type": "string",
"default": "en",
"description": "Language for titles, ingredient names and URLs."
}
}
}Find dishes from other cuisines that are equivalent to a given dish, from eatmundo's scored equivalence graph (over 10,000 edges across nearly 2,000 recipes from 26 countries). Every edge is evidence-based - shared canonical ingredients - not a language-model guess, and every edge crosses country lines. Use it for "what is the Greek counterpart of lahmacun, and why".
| Argument | Type | Description |
|---|---|---|
| dish* | string | Dish to start from: an eatmundo slug (e.g. "lahmacun") or a plain name ("rice pudding"). Names are resolved through site search; check resolved_by in the result. |
| lang | string | Language for titles, ingredient names and URLs. |
| limit | integer | How many matches to return, best score first. The default of 5 is enough to see whether a cuisine has one clear counterpart or several competing ones. |
| country | string | Restrict matches to one cuisine, ISO 3166-1 alpha-2 (e.g. "GR"). 26 countries are covered. |
| min_score | integer | Minimum match score. Defaults to 0 on purpose: 320 dishes only have below-threshold nearest matches, and a default of 50 would silently return nothing for them. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"dish"
],
"properties": {
"dish": {
"type": "string",
"minLength": 2,
"description": "Dish to start from: an eatmundo slug (e.g. \"lahmacun\") or a plain name (\"rice pudding\"). Names are resolved through site search; check resolved_by in the result."
},
"lang": {
"enum": [
"en",
"tr",
"de",
"fr",
"es",
"it",
"el"
],
"type": "string",
"default": "en",
"description": "Language for titles, ingredient names and URLs."
},
"limit": {
"type": "integer",
"default": 5,
"maximum": 20,
"minimum": 1,
"description": "How many matches to return, best score first. The default of 5 is enough to see whether a cuisine has one clear counterpart or several competing ones."
},
"country": {
"type": "string",
"maxLength": 2,
"minLength": 2,
"description": "Restrict matches to one cuisine, ISO 3166-1 alpha-2 (e.g. \"GR\"). 26 countries are covered."
},
"min_score": {
"type": "integer",
"default": 0,
"maximum": 100,
"minimum": 0,
"description": "Minimum match score. Defaults to 0 on purpose: 320 dishes only have below-threshold nearest matches, and a default of 50 would silently return nothing for them."
}
}
}Full recipe for one dish: steps, FAQ, image credit, and ingredients with PARSED quantities (amount, unit, and a normalised base in grams or millilitres where the quantity is measurable). Count-based lines like "3 onions" carry a gram estimate only where a per-item weight is known. Pass servings to rescale the ingredient quantities; the steps keep the original amounts. adaptations lists the diets (vegan, vegetarian, halal, dairy-free, pescatarian) the dish can be fully converted to, with each swap marked substitute (same dish) or adaptation (a different dish).
| Argument | Type | Description |
|---|---|---|
| lang | string | Language for titles, ingredient names and URLs. |
| slug* | string | Recipe slug in any of the 7 languages, or a dish name (resolved by search). |
| servings | integer | Rescale ingredient quantities to this many servings. The dish's own count is returned as original_servings. Steps are NOT rescaled: they keep the amounts of the original recipe. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"slug"
],
"properties": {
"lang": {
"enum": [
"en",
"tr",
"de",
"fr",
"es",
"it",
"el"
],
"type": "string",
"default": "en",
"description": "Language for titles, ingredient names and URLs."
},
"slug": {
"type": "string",
"minLength": 2,
"description": "Recipe slug in any of the 7 languages, or a dish name (resolved by search)."
},
"servings": {
"type": "integer",
"maximum": 100,
"minimum": 1,
"description": "Rescale ingredient quantities to this many servings. The dish's own count is returned as original_servings. Steps are NOT rescaled: they keep the amounts of the original recipe."
}
}
}Search nearly 2,000 dishes from 26 cuisines by text, country, category, preparation technique, or canonical ingredient. Every ingredient in the corpus is linked to a canonical entity, so an ingredient filter also catches translations and spelling variants. Use it to get a slug for the other tools.
| Argument | Type | Description |
|---|---|---|
| form | string | Preparation technique. One of: soup, stew, stir-fry, grill-roast, fritter, dumpling, stuffed-vegetable, flatbread-pastry, noodle, rice, cold-salad, dip-spread, pickle-ferment, egg, sandwich-wrap, porridge-mash, casserole-bake, cured-preserved, composed-plate, meat-salad, pancake-batter, marinated-cooked, syrup-pastry, fried-dough-sweet, cake, cookie, custard-pudding, sweet-pie-tart, fruit-dessert, frozen, confection, sweet-porridge, glutinous-dumpling, sweet-bread, layered-assembly, filled-pastry, sweet-pancake, starch-gel, hot-infusion, cold-cooler, juice, smoothie-shake, hot-milk-drink, fermented-drink, alcoholic-mixed, alcoholic-brew. |
| lang | string | Language for titles, ingredient names and URLs. |
| limit | integer | Results per page (max 25). |
| query | string | Free text; needs at least 2 characters to take effect. |
| offset | integer | Rows to skip for paging. Pass back the `next_offset` from the previous response; it is null when there is no further page. |
| country | string |
Find what can replace a single ingredient, optionally under a dietary constraint (vegan, vegetarian, halal, dairy-free, pescatarian). Each result is marked "substitute" (same dish) or "adaptation" (result is a meaningfully different dish) - most swaps forced by a diet exclusion are adaptations, and the tool says so rather than overselling a swap as if the dish stayed the same. Precomputed and model-verified, not generated on the fly.
| Argument | Type | Description |
|---|---|---|
| lang | string | Language for titles, ingredient names and URLs. |
| limit | integer | Max substitutes to return, best first. |
| context | string | Dietary constraint the substitute must satisfy. Omit for the single best general substitute with no diet filter. Other constraints (gluten-free, allergen-free) are not supported - the corpus has no gluten/allergen data, so the tool would have to guess, and it does not. |
| ingredient* | string | Ingredient name in any of the 7 site languages, or its English canonical form (e.g. "pork belly", "domuz göbeği", "Schweinebauch"). |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"ingredient"
],
"properties": {
"lang": {
"enum": [
"en",
"tr",
"de",
"fr",
"es",
"it",
"el"
],
"type": "string",
"default": "en",
"description": "Language for titles, ingredient names and URLs."
},
"limit": {
"type": "integer",
"default": 3,
"maximum": 5,
"minimum": 1,
"description": "Max substitutes to return, best first."
},
"context": {
"enum": [
"vegan",
"vegetarian",
"halal",
"dairy-free",
"pescatarian"
],
"type": "string",
"description": "Dietary constraint the substitute must satisfy. Omit for the single best general substitute with no diet filter. Other constraints (gluten-free, allergen-free) are not supported - the corpus has no gluten/allergen data, so the tool would have to guess, and it does not."
},
"ingredient": {
"type": "string",
"minLength": 1,
"description": "Ingredient name in any of the 7 site languages, or its English canonical form (e.g. \"pork belly\", \"domuz göbeği\", \"Schweinebauch\")."
}
}
}Build a menu of up to 7 dinners, either one cuisine per day ("world") or all from one country. Honours diet exclusions (pork, beef, meat, fish, dairy, egg, alcohol), vegetarian/vegan/pescatarian requirements, a prep-time ceiling and a budget mode that reuses ingredients. When a constraint cannot be met it is relaxed and the relaxation is reported, never hidden.
| Argument | Type | Description |
|---|---|---|
| days | integer | How many days to plan, 1-7. |
| lang | string | Language for titles, ingredient names and URLs. |
| mode | string | "world" = a different cuisine each day; "single" = one country. |
| seed | integer | Same seed + same options = same menu. |
| budget | boolean | Favour weeks that reuse ingredients across days. |
| country | string | Required when mode is "single". |
| exclude | array | Ingredient attributes to avoid entirely: pork, beef, meat, fish, dairy, egg, alcohol. |
| require | string | Diet every dish must satisfy. This is a WHITELIST and differs from `exclude`, which only removes single ingredient attributes: "vegan" is not the same as excluding meat. |
| ISO 3166-1 alpha-2 cuisine filter. |
| category | string | Dish type. DRINK covers both alcoholic and non-alcoholic; DESSERT is separate from FOOD, so a query for a sweet dish returns nothing under FOOD. |
| ingredients | array | Canonical ingredient names (e.g. ["tomato","garlic"]). A dish matches if it has ANY of them, but results are ranked by how many it has, then by how large a share of the dish's ingredient list they make up (matched / total ingredient lines - among equal matches, dishes with shorter lists come first). Unrecognised names are reported back, not ignored. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"form": {
"type": "string",
"description": "Preparation technique. One of: soup, stew, stir-fry, grill-roast, fritter, dumpling, stuffed-vegetable, flatbread-pastry, noodle, rice, cold-salad, dip-spread, pickle-ferment, egg, sandwich-wrap, porridge-mash, casserole-bake, cured-preserved, composed-plate, meat-salad, pancake-batter, marinated-cooked, syrup-pastry, fried-dough-sweet, cake, cookie, custard-pudding, sweet-pie-tart, fruit-dessert, frozen, confection, sweet-porridge, glutinous-dumpling, sweet-bread, layered-assembly, filled-pastry, sweet-pancake, starch-gel, hot-infusion, cold-cooler, juice, smoothie-shake, hot-milk-drink, fermented-drink, alcoholic-mixed, alcoholic-brew."
},
"lang": {
"enum": [
"en",
"tr",
"de",
"fr",
"es",
"it",
"el"
],
"type": "string",
"default": "en",
"description": "Language for titles, ingredient names and URLs."
},
"limit": {
"type": "integer",
"default": 10,
"maximum": 25,
"minimum": 1,
"description": "Results per page (max 25)."
},
"query": {
"type": "string",
"description": "Free text; needs at least 2 characters to take effect."
},
"offset": {
"type": "integer",
"default": 0,
"maximum": 5000,
"minimum": 0,
"description": "Rows to skip for paging. Pass back the `next_offset` from the previous response; it is null when there is no further page."
},
"country": {
"type": "string",
"maxLength": 2,
"minLength": 2,
"description": "ISO 3166-1 alpha-2 cuisine filter."
},
"category": {
"enum": [
"FOOD",
"DESSERT",
"DRINK"
],
"type": "string",
"description": "Dish type. DRINK covers both alcoholic and non-alcoholic; DESSERT is separate from FOOD, so a query for a sweet dish returns nothing under FOOD."
},
"ingredients": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 10,
"description": "Canonical ingredient names (e.g. [\"tomato\",\"garlic\"]). A dish matches if it has ANY of them, but results are ranked by how many it has, then by how large a share of the dish's ingredient list they make up (matched / total ingredient lines - among equal matches, dishes with shorter lists come first). Unrecognised names are reported back, not ignored."
}
}
}| time_limit | integer | Max prep time in minutes; closed set (30/45/60). The generator relaxes it automatically if too few cuisines qualify, and reports that in relaxations. |
| include_extras | boolean | Add 2 desserts and 2 drinks (never alcoholic). |
| exclude_countries | array | Cuisines to keep out of the plan, ISO 3166-1 alpha-2. Only meaningful when mode is "world"; excluding too many leaves the generator with too few cuisines to fill the week. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"days": {
"type": "integer",
"default": 7,
"maximum": 7,
"minimum": 1,
"description": "How many days to plan, 1-7."
},
"lang": {
"enum": [
"en",
"tr",
"de",
"fr",
"es",
"it",
"el"
],
"type": "string",
"default": "en",
"description": "Language for titles, ingredient names and URLs."
},
"mode": {
"enum": [
"world",
"single"
],
"type": "string",
"default": "world",
"description": "\"world\" = a different cuisine each day; \"single\" = one country."
},
"seed": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": 1,
"description": "Same seed + same options = same menu."
},
"budget": {
"type": "boolean",
"default": false,
"description": "Favour weeks that reuse ingredients across days."
},
"country": {
"type": "string",
"maxLength": 2,
"minLength": 2,
"description": "Required when mode is \"single\"."
},
"exclude": {
"type": "array",
"items": {
"enum": [
"pork",
"beef",
"meat",
"fish",
"dairy",
"egg",
"alcohol"
],
"type": "string"
},
"description": "Ingredient attributes to avoid entirely: pork, beef, meat, fish, dairy, egg, alcohol."
},
"require": {
"enum": [
"vegetarian",
"vegan",
"pescatarian"
],
"type": "string",
"description": "Diet every dish must satisfy. This is a WHITELIST and differs from `exclude`, which only removes single ingredient attributes: \"vegan\" is not the same as excluding meat."
},
"time_limit": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "Max prep time in minutes; closed set (30/45/60). The generator relaxes it automatically if too few cuisines qualify, and reports that in relaxations."
},
"include_extras": {
"type": "boolean",
"default": true,
"description": "Add 2 desserts and 2 drinks (never alcoholic)."
},
"exclude_countries": {
"type": "array",
"items": {
"type": "string",
"maxLength": 2,
"minLength": 2
},
"maxItems": 30,
"description": "Cuisines to keep out of the plan, ISO 3166-1 alpha-2. Only meaningful when mode is \"world\"; excluding too many leaves the generator with too few cuisines to fill the week."
}
}
}