Skip to main content
Glama
mcp-recipes

mcp-recipes

mcp-recipes

npm CI license MCP Registry Glama M8ven LobeHub Install in Cursor Install in VS Code

Recipes live on many sites, and each one writes them its own way: a French cooking site publishes in French, with its own measures and its own idea of what a serving is, and a wiki cookbook in English, with equipment lists and prose the first has no field for. Asking a question of one of them answers about one of them.

This server reads six. Three publish in French, Marmiton, Ptitchef and Supertoinette; two in English, the Wikibooks Cookbook and BBC Good Food; and one in Spanish, Pequerecetas. You can search them all with one question, read a recipe from any of them in one shape, put several versions of the same dish side by side, and rescale any ingredient list. It needs no API key and no account.

Version française


Install

One-click install

Install in Cursor Install in VS Code

Claude Code

claude mcp add recipes -- npx -y mcp-recipes

Claude Desktop, Cursor, and any client using the standard config format

{
  "mcpServers": {
    "recipes": {
      "command": "npx",
      "args": ["-y", "mcp-recipes"]
    }
  }
}

Node 24 or later is required, and no environment variable has to be set.

With Docker

{
  "mcpServers": {
    "recipes": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "ghcr.io/smeet666/mcp-recipes:4.1.0"]
    }
  }
}

-i keeps stdin open, which is where the protocol travels, and -t is left out because a TTY rewrites the stream. The container needs outbound HTTPS to www.marmiton.org, api.wikimedia.org, www.ptitchef.com, www.bbcgoodfood.com, www.supertoinette.com and www.pequerecetas.com, and nothing else: no volume, no port, no credential.

Bundle, without npm

Download mcp-recipes-4.1.0.mcpb from the latest release and open it. A client that supports MCP bundles installs it on its own, with no npm and no configuration file to edit. The bundle carries its dependencies, so nothing is fetched at install time.

Related MCP server: mealplan-mcp

What you can ask

  • "Find me carbonara recipes, from wherever you can."

  • "Compare the French and English versions of that dish."

  • "Read the second one for eight people."

  • "Which of them uses cream?"

  • "Scale this list from my notebook by 1.5."

The ordinary path runs from a search to a reading: a row carries an id naming its source, and get_recipe takes it.

The sources

Source

Site

Language

marmiton

www.marmiton.org

French

cookbook

Wikibooks Cookbook

English

ptitchef

www.ptitchef.com

French

goodfood

www.bbcgoodfood.com

English

supertoinette

www.supertoinette.com

French

pequerecetas

www.pequerecetas.com

Spanish

A row's id names its source, so an identifier read from one answer goes back to the right site. Counts are never added across sources, and a source that failed is reported as having failed rather than as having found nothing.

Each site is read at its own pace: two of them ask for three seconds between requests, and a setting posted for all of them can only make this server more patient than the slowest asks for.

Two of these sites file something other than a recipe at the address a recipe lives at. The Wikibooks Cookbook keeps pages about an ingredient beside the recipes using it, and Pequerecetas publishes articles that gather recipes. A search says so, and get_recipe says what it read off the page.

Tools

Tool

What it does

search_recipes

Searches every source with one question.

get_recipe

Reads one recipe from any source, in one shape.

compare_recipes

Puts several versions of the same dish side by side.

scale_ingredients

Rescales any ingredient list, with no request to any site.

search_recipes

Searches every source with one question.

Argument

Type

Required

What it does

query

string, 1 to 200 characters

yes

The dish or the ingredient to look for.

limit_per_source

integer, 1 to 25, default 5

no

Rows to keep from each source.

sources

array of source ids

no

Ask these sources alone.

fan_out

boolean, default true

no

Also send each source shorter wordings derived from the question.

In return: results, rows carrying id, which get_recipe takes; source and source_name saying which site published the row; title; url; image_url; and an excerpt where the source offers one. per_source gives one report per site with its status, reading answered or failed, the count it contributed, and its reported_total alongside reported_total_means, which says what that number counts on that site. names_the_dish says how many of that site's rows carry the dish in their title, out of count: a search index answers the words it is handed, so a site can offer rows and none of them be the dish. order says in words how the list was built.

get_recipe

Reads one recipe from any source, in one shape.

Argument

Type

Required

What it does

id

string, 1 to 500 characters

yes

The identifier a row carries, such as marmiton:44078. Two sources address a recipe by a bare number, so spell an id with its source.

servings

integer, 1 to 500

no

Rescale the ingredients to this many servings.

sections

array of ingredients, steps, times, nutrition, tips, equipment, default ["ingredients", "steps"]

no

Which parts to return.

max_steps

integer, 1 to 100, default 20

no

Steps to serve.

max_gathered

integer, 1 to 500, default 30

no

Recipes and headings to return from an address that gathers recipes.

max_step_chars

integer, 80 to 4000, default 600

no

Characters kept per step.

In return: kind says what the address held. A recipe answer carries recipe and no collection; a collection answer carries collection and no recipe, and is an article gathering other recipes, with the headings it is built from and the recipes it points at, each of them readable with get_recipe.

A recipe comes in the shape every source is rendered into, whichever published it: its title, its address, its ingredients with each line's scaling and is_equipment, its steps, and the sections asked for. A field one source publishes and another has no notion of comes back absent rather than invented. rest_minutes carries a resting time from a source that prints one apart, and is in no other time here. steps_as_one_block says when a source published its method as one block of prose rather than as steps. withheld names a part a source keeps for its subscribers, which is a part the page has rather than a part that could not be read. scaling_summary counts the lines four ways, and the four add up to the list. Raise max_step_chars when a step was cut mid-sentence.

compare_recipes

Puts several versions of the same dish side by side.

Argument

Type

Required

What it does

dish

string, 1 to 200 characters

yes

The dish to compare.

servings

integer, 1 to 500

no

Rescale every version to this many servings.

sections

array of ingredients, steps, times, nutrition, tips, equipment, default ["ingredients"]

no

Which parts to return per version.

max_steps

integer, 1 to 100, default 10

no

Steps to serve per version.

max_step_chars

integer, 80 to 4000, default 600

no

Characters kept per step.

sources

array of source ids

no

Compare these sources alone.

In return: versions, one recipe per source that answered, all rescaled to the same number of servings so their quantities can be read against each other, and differences, what separates them. per_source reports each site as a search does.

scale_ingredients

Rescales any ingredient list, with no request to any site.

Argument

Type

Required

What it does

ingredients

array of 1 to 200 lines

yes

The lines to rescale.

factor

number, up to 1000

one of two

The multiplier to apply.

from_servings

integer, 1 to 500

one of two

How many servings the list is written for.

to_servings

integer, 1 to 500

one of two

How many servings are wanted.

language

auto, fr, en or es, default auto

no

How each line is read.

Pass factor, or the from_servings and to_servings pair. auto reads each line on its own, which is what a list holding more than one language needs; naming a language reads every line that way.

In return: the rescaled lines in the shape get_recipe returns, each with its scaling.

Rescaling the quantities

A quantity is stated in the unit that suits it, so a line can come back in a different unit from the one the recipe used: 200 g multiplied by twenty reads 4 kg.

How finely an ingredient can be divided depends on what it is. A baguette can be cut in two, in three or in four; an egg cannot be shared out. A quantity landing between the two is rounded, and the rescaled recipe then departs a little from the proportions of the original. The line carries rounded, and its note says what was done.

The sources write their quantities in their own languages, and a line is read in the language it was written in. The figures are this server's arithmetic, so say they were recomputed when you show them.

What an answer states about the sources

Every answer accounts for each source separately. A site that failed, one nobody asked, and one that answered with nothing are three different things, and they are reported as three. A total stays beside the source that published it, with what that source counts when it says it: one site counts a whole category, another counts the rows it served, and a third publishes no total at all.

Configuration

Every variable is optional. Set them in the env block of your client config.

Variable

Default

What it does

RECIPES_USER_AGENT

the project identity

Names your application to the sites, with an address where a person can be reached.

RECIPES_MIN_INTERVAL_MS

1000

Gap between two requests to one site, from 500 to 60000.

RECIPES_TIMEOUT_MS

20000

Deadline for one request, from 1000 to 120000.

RECIPES_MAX_RETRIES

3

Attempts after a transient failure, from 0 to 8.

RECIPES_CACHE_TTL_MS

900000

How long an answer stays in memory, from 0 to 86400000.

RECIPES_CACHE_MAX_ENTRIES

200

Answers held in memory at once, from 1 to 5000.

RECIPES_LOG_LEVEL

error

silent, error, info or debug, written to stderr.

A value outside its range falls back to the default, and the reason is written to stderr.

Errors

Every failure carries one of six codes, a message, and where it helps a hint naming the next move.

Code

What happened

What to do

not_found

A source answered, and holds no such recipe.

Check the identifier with search_recipes.

invalid_input

The arguments were refused before any request went out.

Read the message, which names the argument.

rate_limited

A source asked this client to slow down.

Wait, then call again with the same arguments. The recipe is still there.

parse_failure

A page loaded and the expected content was absent.

Report it at the issue tracker.

network_error

The request did not complete.

Try again shortly.

timeout

The request passed its deadline.

Raise RECIPES_TIMEOUT_MS, or ask for fewer rows.

A source that failed is reported per source rather than failing the whole answer, so one silent site never hides the other.

As a library

The layer reading the sites is published on its own, with its pacing, its cache and its errors, and with no protocol attached.

import { RecipesClient } from "mcp-recipes/client";

const client = new RecipesClient();
const { rows, reports } = await client.searchRecipes("carbonara", 3);
console.log(
  rows.length,
  reports.map((report) => report.status),
);

const { recipe } = await client.getRecipe(rows[0].id);

searchRecipes(query, limitPerSource, sources?, options?) answers { rows, reports }: one report per source, saying whether it answered and what its own count measured, so a source that failed is never read as a source that holds nothing. getRecipe(id) answers { recipe, cached, read }, and throws an error carrying one of the six codes. client.profiles lists the sources the build registers.

The scaler is published separately at mcp-recipes/scale, and works offline on any list:

import { scaleIngredients } from "mcp-recipes/scale";

scaleIngredients(["200 g de harina", "4 oeufs", "1 cup milk"], { factor: 2 });

Each site keeps its own pace, and the floors hold here as well.

Pacing and attribution

Each site is paced on its own, one request at a time. Every site holds a floor of its own that no configuration goes under: half a second for Marmiton and the Cookbook, one second for Ptitchef and BBC Good Food, three seconds for Supertoinette and Pequerecetas. A setting posted for every source can raise a site's spacing and never lower it. Asking every site at once therefore costs each of them one request, never two. The User-Agent always ends with the project identity and an address where a person can be reached.

Every row carries the address of the recipe's own page and the name of the site that published it. The Cookbook pages are published under CC BY-SA 4.0, which asks that what is built on them be shared under the same licence. Marmiton, Ptitchef, BBC Good Food, Supertoinette and Pequerecetas state no terms on a recipe page, and their recipes belong to those sites and to the cooks who wrote them. Silence is not a grant, so credit the site and link the page you took a recipe from.

A recipe BBC Good Food keeps for its subscribers comes back without its ingredients and its method, named as a recipe held back, with the address of its page. This server does not reconstruct what that site chose to sell.

Two figures the sites publish are not repeated here. A difficulty is a word each site writes its own way, on no scale any of them publishes, so it sits on no axis along which two versions could be put. A cost is a price in euros on one site and a rank inside its own list on another, and one field holding both would invite them to be compared.

This MCP server is an unofficial project, with no affiliation to any of the sites it reads.

Privacy

This server collects nothing about you and sends nothing to its author. It runs on your machine, contacts www.marmiton.org, api.wikimedia.org, www.ptitchef.com, www.bbcgoodfood.com, www.supertoinette.com and www.pequerecetas.com and nothing else, holds its answers in memory while it runs, and writes nothing to disk. PRIVACY.md states what a request carries and which settings change any of it.

Development

npm install
npm run build:fixtures
npm test
npm run check

Tests run against generated fixtures and make no network request. The live suite, npm run test:live, makes one request per route and runs nightly against the sites themselves.

Contributing

Bugs, questions and ideas belong in the issue tracker. Pull requests are welcome; opening an issue first helps agree on the shape of the change. See CONTRIBUTING.md.

License

MIT, see LICENSE. The recipes belong to the sites that published them and to their authors.


mcp-recipes (français)

English version

Les recettes vivent sur beaucoup de sites, et chacun les écrit à sa façon : un site de cuisine français publie en français, avec ses mesures et son idée de ce qu'est une part, et un wiki de cuisine en anglais, avec des listes de matériel et une prose pour lesquelles le premier n'a aucun champ. Poser une question à l'un d'eux répond au sujet de l'un d'eux.

Ce serveur en lit six. Trois publient en français, Marmiton, Ptitchef et Supertoinette ; deux en anglais, le Cookbook des Wikibooks et BBC Good Food ; un en espagnol, Pequerecetas. On peut chercher dans les six avec une seule question, lire une recette de n'importe lequel sous une seule forme, mettre plusieurs versions d'un même plat côte à côte, et adapter n'importe quelle liste d'ingrédients. Aucune clé d'API, aucun compte.

Installation

Installation en un clic

Install in Cursor Install in VS Code

Claude Code

claude mcp add recipes -- npx -y mcp-recipes

Claude Desktop, Cursor, et tout client au format de configuration standard

{
  "mcpServers": {
    "recipes": {
      "command": "npx",
      "args": ["-y", "mcp-recipes"]
    }
  }
}

Node 24 ou plus récent est nécessaire, et aucune variable d'environnement n'est à renseigner.

Avec Docker

{
  "mcpServers": {
    "recipes": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "ghcr.io/smeet666/mcp-recipes:4.1.0"]
    }
  }
}

-i garde l'entrée standard ouverte, qui est le canal du protocole, et -t est omis parce qu'un TTY réécrit le flux. Le conteneur a besoin d'un accès HTTPS sortant vers www.marmiton.org, api.wikimedia.org, www.ptitchef.com, www.bbcgoodfood.com, www.supertoinette.com et www.pequerecetas.com, et de rien d'autre : aucun volume, aucun port, aucun identifiant.

Bundle, sans npm

Téléchargez mcp-recipes-4.1.0.mcpb depuis la dernière publication et ouvrez-le. Un client qui gère les bundles MCP l'installe seul, sans npm et sans fichier de configuration à modifier. Le bundle emporte ses dépendances, donc rien n'est téléchargé à l'installation.

Ce qu'on peut demander

  • « Trouve-moi des recettes de carbonara, d'où que tu puisses. »

  • « Compare les versions française et anglaise de ce plat. »

  • « Lis-moi la seconde pour huit personnes. »

  • « Laquelle utilise de la crème ? »

  • « Multiplie par 1,5 cette liste de mon carnet. »

Le chemin ordinaire va d'une recherche à une lecture : une ligne porte un id qui nomme sa source, et get_recipe le reprend.

Les sources

Source

Site

Langue

marmiton

www.marmiton.org

français

cookbook

Cookbook Wikibooks

anglais

ptitchef

www.ptitchef.com

français

goodfood

www.bbcgoodfood.com

anglais

supertoinette

www.supertoinette.com

français

pequerecetas

www.pequerecetas.com

espagnol

L'id d'une ligne nomme sa source, donc un identifiant lu dans une réponse retourne vers le bon site. Les comptes ne sont jamais additionnés entre sources, et une source qui a échoué est rapportée comme ayant échoué plutôt que comme n'ayant rien trouvé.

Chaque site est lu à son propre rythme : deux d'entre eux demandent trois secondes entre deux requêtes, et un réglage posé pour tous ne peut que rendre ce serveur plus patient que ce que le plus lent demande.

Deux de ces sites rangent autre chose qu'une recette à l'adresse où vit une recette. Le Cookbook des Wikibooks garde des pages sur un ingrédient à côté des recettes qui l'emploient, et Pequerecetas publie des articles qui rassemblent des recettes. Une recherche le dit, et get_recipe dit ce qu'il a lu sur la page.

Les outils

Outil

Ce qu'il fait

search_recipes

Cherche dans toutes les sources avec une seule question.

get_recipe

Lit une recette de n'importe quelle source, sous une seule forme.

compare_recipes

Met plusieurs versions d'un même plat côte à côte.

scale_ingredients

Adapte n'importe quelle liste d'ingrédients, sans requête.

search_recipes

Cherche dans toutes les sources avec une seule question.

Argument

Type

Requis

Ce qu'il fait

query

chaîne, 1 à 200 caractères

oui

Le plat ou l'ingrédient cherché.

limit_per_source

entier, 1 à 25, défaut 5

non

Lignes à garder de chaque source.

sources

tableau d'identifiants de source

non

N'interroger que ces sources.

fan_out

booléen, défaut true

non

Envoyer aussi à chaque source des formulations plus courtes tirées de la question.

En retour : results, des lignes portant id, que get_recipe reprend ; source et source_name qui disent quel site a publié la ligne ; title ; url ; image_url ; et un excerpt là où la source en propose un. per_source donne un rapport par site avec son status, valant answered ou failed, le count qu'il a fourni, et son reported_total accompagné de reported_total_means, qui dit ce que ce nombre compte sur ce site. names_the_dish dit combien des lignes de ce site portent le plat dans leur titre, sur count : un index de recherche répond aux mots qu'on lui tend, donc un site peut rendre des lignes dont aucune n'est le plat. order dit en mots comment la liste a été bâtie.

get_recipe

Lit une recette de n'importe quelle source, sous une seule forme.

Argument

Type

Requis

Ce qu'il fait

id

chaîne, 1 à 500 caractères

oui

L'identifiant d'une ligne, tel que marmiton:44078. Deux sources adressent une recette par un nombre nu : écrivez l'id avec sa source.

servings

entier, 1 à 500

non

Adapte les ingrédients à ce nombre de parts.

sections

tableau de ingredients, steps, times, nutrition, tips, equipment, défaut ["ingredients", "steps"]

non

Les parties à rendre.

max_gathered

entier, 1 à 500, défaut 30

non

Recettes et intertitres rendus pour une adresse qui rassemble des recettes.

max_steps

entier, 1 à 100, défaut 20

non

Étapes à servir.

max_step_chars

entier, 80 à 4000, défaut 600

non

Caractères gardés par étape.

En retour : kind dit ce que l'adresse portait. Une réponse recipe porte recipe et pas de collection ; une réponse collection porte collection et pas de recipe, et c'est un article rassemblant d'autres recettes, avec les headings dont il est bâti et les recipes vers lesquelles il pointe, chacune lisible par get_recipe.

Une recette vient dans la forme où toutes les sources sont rendues, quelle que soit celle qui l'a publiée : son titre, son adresse, ses ingrédients avec le scaling et l'is_equipment de chaque ligne, ses étapes, et les parties demandées. Un champ qu'une source publie et dont une autre n'a pas la notion revient absent plutôt qu'inventé. rest_minutes porte le temps de repos d'une source qui l'imprime à part, et il n'entre dans aucun autre temps rendu ici. steps_as_one_block dit quand une source a publié sa méthode d'un seul bloc de prose plutôt qu'en étapes. scaling_summary compte les lignes de quatre façons, et les quatre font le total de la liste. withheld nomme la partie qu'une source réserve à ses abonnés, qui est une partie que la page porte et non une partie illisible. Augmentez max_step_chars quand une étape a été coupée au milieu d'une phrase.

compare_recipes

Met plusieurs versions d'un même plat côte à côte.

Argument

Type

Requis

Ce qu'il fait

dish

chaîne, 1 à 200 caractères

oui

Le plat à comparer.

servings

entier, 1 à 500

non

Adapte chaque version à ce nombre de parts.

sections

tableau de ingredients, steps, times, nutrition, tips, equipment, défaut ["ingredients"]

non

Les parties à rendre par version.

max_steps

entier, 1 à 100, défaut 10

non

Étapes à servir par version.

max_step_chars

entier, 80 à 4000, défaut 600

non

Caractères gardés par étape.

sources

tableau d'ids de source

non

Ne compare que ces sources.

En retour : versions, une recette par source ayant répondu, toutes adaptées au même nombre de parts pour que leurs quantités se lisent l'une contre l'autre, et differences, ce qui les sépare. per_source rapporte chaque site comme le fait une recherche.

scale_ingredients

Adapte n'importe quelle liste d'ingrédients, sans requête à aucun site.

Argument

Type

Requis

Ce qu'il fait

ingredients

tableau de 1 à 200 lignes

oui

Les lignes à adapter.

factor

nombre, jusqu'à 1000

l'un des deux

Le multiplicateur à appliquer.

from_servings

entier, 1 à 500

l'un des deux

Le nombre de parts de la liste d'origine.

to_servings

entier, 1 à 500

l'un des deux

Le nombre de parts voulu.

language

auto, fr, en ou es, défaut auto

non

Comment chaque ligne est lue.

Passez factor, ou le couple from_servings et to_servings. auto lit chaque ligne pour elle-même, ce dont a besoin une liste portant plusieurs langues ; nommer une langue lit toutes les lignes ainsi.

En retour : les lignes adaptées dans la forme que rend get_recipe, chacune avec son scaling et son is_equipment, vrai pour une ligne qui nomme un outil et qu'on laisse telle quelle. scaled_count, rounded_count, unscaled_count et equipment_count font le total des lignes envoyées.

L'adaptation des quantités

Une quantité est exprimée dans l'unité qui lui convient. Après adaptation, une ligne peut donc apparaître dans une autre unité que celle de la recette : 200 g multipliés par vingt donnent 4 kg.

La finesse à laquelle un ingrédient se coupe dépend de sa nature. Une baguette se coupe en deux, en trois ou en quatre ; un oeuf ne se partage pas. Une quantité qui tombe entre les deux est donc arrondie, et la recette adaptée s'écarte alors un peu des proportions de l'originale. La ligne porte rounded, et sa note dit ce qui a été fait.

Les sources écrivent leurs quantités dans leur propre langue, et une ligne est lue dans la langue où elle a été écrite. Les chiffres sont l'arithmétique de ce serveur, donc dites qu'ils ont été recalculés quand vous les montrez.

Ce qu'une réponse dit des sources

Chaque réponse rend compte de chaque source séparément. Un site qui a échoué, un que personne n'a interrogé et un qui a répondu vide sont trois choses différentes, et elles sont rapportées comme trois. Un total reste à côté de la source qui l'a publié, avec ce que cette source compte en le disant : l'un compte une catégorie entière, un autre compte les lignes qu'il a servies, et un troisième ne publie aucun total.

Configuration

Chaque variable est facultative. Elles se posent dans le bloc env de la configuration du client.

Variable

Défaut

Ce qu'elle fait

RECIPES_USER_AGENT

l'identité du projet

Nomme votre application auprès des sites, avec une adresse où joindre une personne.

RECIPES_MIN_INTERVAL_MS

1000

Écart entre deux requêtes vers un même site, de 500 à 60000.

RECIPES_TIMEOUT_MS

20000

Délai d'une requête, de 1000 à 120000.

RECIPES_MAX_RETRIES

3

Tentatives après un échec passager, de 0 à 8.

RECIPES_CACHE_TTL_MS

900000

Durée pendant laquelle une réponse reste en mémoire, de 0 à 86400000.

RECIPES_CACHE_MAX_ENTRIES

200

Réponses gardées en mémoire à la fois, de 1 à 5000.

RECIPES_LOG_LEVEL

error

silent, error, info ou debug, écrit sur la sortie d'erreur.

Une valeur hors de sa plage retombe sur le défaut, et la raison est écrite sur la sortie d'erreur.

Erreurs

Chaque échec porte un des six codes, un message, et quand cela aide une indication du geste suivant.

Code

Ce qui s'est passé

Que faire

not_found

Une source a répondu, et n'a pas cette recette.

Vérifiez l'identifiant avec search_recipes.

invalid_input

Les arguments ont été refusés avant toute requête.

Lisez le message, qui nomme l'argument.

rate_limited

Une source demande à ce client de ralentir.

Attendez, puis rappelez avec les mêmes arguments. La recette est toujours là.

parse_failure

Une page a chargé et le contenu attendu est absent.

Signalez-le sur le suivi d'incidents.

network_error

La requête n'a pas abouti.

Réessayez sous peu.

timeout

La requête a dépassé son délai.

Augmentez RECIPES_TIMEOUT_MS, ou demandez moins de lignes.

Une source qui échoue est rapportée source par source plutôt que de faire échouer toute la réponse, donc un site silencieux n'en cache jamais un autre.

Comme bibliothèque

La couche qui lit les sites est publiée seule, avec son rythme, son cache et ses erreurs, sans protocole attaché.

import { RecipesClient } from "mcp-recipes/client";

const client = new RecipesClient();
const { rows, reports } = await client.searchRecipes("carbonara", 3);
console.log(
  rows.length,
  reports.map((report) => report.status),
);

const { recipe } = await client.getRecipe(rows[0].id);

searchRecipes(query, limitPerSource, sources?, options?) répond { rows, reports } : un rapport par source, disant si elle a répondu et ce que son propre compte mesure, pour qu'une source en échec ne se lise jamais comme une source qui ne détient rien. getRecipe(id) répond { recipe, cached, read }, et lève une erreur portant un des six codes. client.profiles énumère les sources que cette construction enregistre.

La mise à l'échelle est publiée à part, sous mcp-recipes/scale, et travaille hors ligne sur n'importe quelle liste :

import { scaleIngredients } from "mcp-recipes/scale";

scaleIngredients(["200 g de harina", "4 oeufs", "1 cup milk"], { factor: 2 });

Chaque site garde son propre rythme, et les planchers tiennent également ici.

Rythme et attribution

Chaque site est cadencé pour lui-même, une requête à la fois. Chaque site tient un plancher qui lui est propre et sous lequel aucune configuration ne descend : une demi-seconde pour Marmiton et le Cookbook, une seconde pour Ptitchef et BBC Good Food, trois secondes pour Supertoinette et Pequerecetas. Un réglage posé pour toutes les sources peut élargir l'écart d'un site, jamais le réduire. Les interroger toutes à la fois coûte donc à chacune une requête, jamais deux. Le User-Agent se termine toujours par l'identité du projet et une adresse où joindre une personne.

Chaque ligne porte l'adresse de la page de la recette et le nom du site qui l'a publiée. Les pages du Cookbook sont publiées sous CC BY-SA 4.0, qui demande que ce qu'on bâtit dessus soit partagé sous la même licence. Marmiton, Ptitchef, BBC Good Food, Supertoinette et Pequerecetas n'énoncent aucune condition sur une page de recette, et leurs recettes appartiennent à ces sites et aux cuisiniers qui les ont écrites. Le silence n'est pas une autorisation : créditez le site et liez la page d'où vient la recette.

Une recette que BBC Good Food réserve à ses abonnés revient sans ses ingrédients ni sa méthode, nommée comme une recette retenue, avec l'adresse de sa page. Ce serveur ne reconstitue pas ce que ce site a choisi de vendre.

Deux chiffres que les sites publient ne sont pas repris ici. Une difficulté est un mot que chaque site écrit à sa façon, sur aucune échelle publiée : elle ne siège sur aucun axe le long duquel deux versions se compareraient. Un coût est un prix en euros sur un site et un rang dans sa propre liste sur un autre, et un seul champ portant les deux inviterait à les comparer.

Ce MCP est un projet non officiel, sans affiliation à aucun des sites qu'il lit.

Confidentialité

Ce serveur ne collecte rien sur vous et n'envoie rien à son auteur. Il tourne sur votre machine, ne joint que www.marmiton.org, api.wikimedia.org, www.ptitchef.com, www.bbcgoodfood.com, www.supertoinette.com et www.pequerecetas.com, garde ses réponses en mémoire le temps qu'il tourne, et n'écrit rien sur le disque. PRIVACY.md dit ce qu'une requête emporte et quels réglages changent cela.

Développement

npm install
npm run build:fixtures
npm test
npm run check

Les tests s'exécutent sur des fixtures engendrées et n'émettent aucune requête. La suite en direct, npm run test:live, émet une requête par route et tourne chaque nuit contre les sites eux-mêmes.

Contribuer

Les anomalies, les questions et les idées ont leur place dans le suivi d'incidents. Les propositions de modification sont bienvenues ; ouvrir un ticket d'abord aide à s'accorder sur la forme du changement. Voir CONTRIBUTING.md.

Licence

MIT, voir LICENSE. Les recettes appartiennent aux sites qui les ont publiées et à leurs auteurs.

Available Tools

4 tools
compare_recipesOne dish, as each source writes itA
Read-onlyIdempotent

Take a dish and show how each source writes it, side by side. Each source's closest match is read in full, and all of them can be rescaled to the same number of servings so the ingredient lists stand comparison. The answer states what differs and leaves it there: the quantities each asks for, what each measures in, what each yields, and which fields each source publishes at all. No version is ranked above another. Some sources carry reader ratings and some have no author and no rating by nature, so there is no score they share. When only one source answers, the answer names that source and shows its version, so a single version is read as the one it is.

Inputs: dish (required), sources, sections, servings, +2 more. Returns: dish, notes, versions, per_source, +1 more

get_recipeRead one recipe, optionally rescaledA
Read-onlyIdempotent

Read one recipe in full: its ingredients, its steps, what it yields, and whatever times, rating and nutrition its source publishes. 'id' must come from search_recipes. It names the source, so this reads the right one without guessing; an identifier no source would have minted is refused, because sending it anywhere would answer about the wrong dish. Pass 'servings' to rescale. Quantities land where a kitchen can follow them: an egg stays whole, anything that pours or cuts can halve, a small measurement moves to a smaller unit before it is rounded, and anything unmultipliable comes back flagged. A page that states no number of servings comes back as published and says so, because dividing by a yield nobody wrote would answer for a number of people the page never claimed. Read 'kind' first. Some sources publish articles gathering other recipes at the same kind of address as a recipe, and such an answer carries 'collection' with the recipes it points at and no 'recipe' at all: there is nothing to cook from that page, and the recipes it lists are read with get_recipe. A part this answer holds nothing for says which of two things happened: the page showed no sign of it, or this server failed to read what the page carries. An empty ingredient list is never evidence that an ingredient is absent from the dish. 'sections' decides what comes back, and 'sections_omitted' names what was left out: a field belonging to an omitted section is empty because nobody asked for it, never because the page states nothing. A field a source does not publish is null, never zero. Credit the source and link the url when you repeat any of it.

Inputs: id (required), sections, servings, max_steps, +2 more. Returns: kind, notes, recipe, collection, +1 more

scale_ingredientsScale an ingredient list, in any language it readsA
Read-onlyIdempotent

Multiply a list of ingredient lines, in French, in English, in Spanish, or in a list holding more than one of them. Give either 'factor', or 'from_servings' and 'to_servings' and the factor is worked out from them. Quantities land where a kitchen can follow them: an egg stays whole because half of one is not something a cook takes out of the shell, while anything that pours, weighs or cuts can halve, a spoonful shrinks into the smaller spoon before it is rounded, and a pinch keeps whatever size a hand gives it while its count is multiplied. Every line comes back with 'scaling': 'scaled' when the arithmetic landed on the exact product, 'rounded' when something had to move for the line to stay usable, 'unscaled' when the line carries nothing to multiply. A rounded line says what it was rounded from and in which direction. No quantity is converted between measuring systems: grams stay grams and cups stay cups, because a conversion changes what the recipe said.

Inputs: ingredients (required), factor, language, to_servings, +1 more. Returns: notes, factor, language, ingredients, +4 more

search_recipesSearch every recipe source at onceA
Read-onlyIdempotent

Search every recipe source this server reads, at the same time, for a dish or an ingredient, and get one merged list. Each row carries the id get_recipe takes, and that id names the source it came from, so nothing has to be guessed afterwards. The sources are written in different languages and count their own results differently, so 'per_source' says what each one answered, what its own number means, and names any that failed. A short list is never evidence of what exists. Not every row opens onto a recipe. Some sources file pages about an ingredient beside the recipes using it, and some publish articles that gather recipes; 'per_source' says in each source's own words what one of its rows can be. Only get_recipe tells them apart, and it says what it read off the page. The query goes to each source's own search as free text. There is no filtering: a word naming a diet, a time or a calorie count matches only where that source's index happens to carry it. Ask in a whole sentence if that is the question. These indexes answer the words they are handed, so a sentence is also sent as the words naming the dish and as the dish word alone, and the rows are the union; 'per_source' lists every wording and what it returned. What the question says the recipe must not hold is set aside from those shorter wordings rather than searched for, and named back in the notes: a negation, an allergy stated as one, a diet named in one word, and the number of people at the table. No source filters on any of it, so open a row with get_recipe and read the ingredient list before calling it suitable. A condition is read with the food on whichever side of it the sentence put one, so 'allergique aux noix' and 'peanut allergy' both name the nut. Where a sentence puts a food on neither side, the notes say a condition was stated and that its food was not read, because naming the wrong word would hide a dish and search for the food being avoided at once. Rows are interleaved one source at a time, since the sources share no score that could order them against each other.

Inputs: query (required), fan_out, sources, limit_per_source. Returns: notes, order, query, results, +2 more

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.4/5.0

    Scored across 4 tools

    Disambiguation4/5

    The four tools have mostly distinct purposes: search discovers recipes, get_recipe reads one in full, scale_ingredients scales arbitrary ingredient lines, and compare_recipes compares versions across sources. There is some overlap because get_recipe can also rescale via 'servings' and compare_recipes can rescale multiple recipes, so an agent may briefly hesitate between scaling pathways. Overall boundaries are clear enough but not perfectly clean.

    Naming Consistency5/5

    All tool names follow a consistent snake_case verb_noun pattern: search_recipes, get_recipe, scale_ingredients, compare_recipes. The verbs are distinct and the resource nouns are predictable. No naming inconsistencies are present.

    Tool Count5/5

    Four tools is well-scoped for a read-only recipe aggregation server. Each tool earns its place by covering discovery, full reading, scaling, and cross-source comparison without redundant endpoints. The surface is small but appropriately focused.

    Completeness4/5

    The core recipe lifecycle is covered: search across sources, read a full recipe, scale ingredients, and compare source versions. Minor gaps remain, such as no explicit source-listing tool or dedicated browsing/filtering operation, though search's 'per_source' reporting mitigates this. Agents can work around these gaps.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Related MCP Connectors

    • Your Recipes, Beautifully Kept. weReci MCP server lets Claude and other MCP clients work with your personal weReci cookbook, the recipes you've imported from the web, social video and scanned family books. Interactive UI in the chat. weReci supports MCP Apps, so in clients that support it, tools return live views instead of plain text: recipe cards, shopping lists and your recipe graph. Clients without MCP Apps support get the same results as text. Find and read recipes: search your collection in plain language, open any recipe in full, or get an overview of what's in your cookbook. Cook with them: scale a recipe to any serving count, with cooking adjustments as well as amounts. Get substitution suggestions with ratios and caveats. Explore connections: browse your recipe graph (shared ingredients, techniques and cuisines), trace the connection between two recipes, and look up where a dish sits on the cuisine map. Themed collections: list the themed groups weReci curates from your cookbook, or ask it to reshuffle them. Shop: build a shopping list from one or more recipes, add or update items, and read the list back. Share: email a recipe to someone. Longer jobs like conceit reshuffles run in the background, with tools to check their progress. Everything is scoped to your own cookbook, or to a shared one you've joined.

      https://wereci.xyz/api/mcp
    • One MCP server for all web data. Scrape, search, crawl, and AI research in one install.

      https://mcp.novada.com/mcp
    • An MCP server that exposes functionalities to use Zomato's services.

      https://mcp-server.zomato.com/mcp
    • Unlock the power of food transparency with our Open Food Facts MCP server. Easily look up any food

    Related MCP Servers

    • A
      license
      B
      quality
      D
      maintenance
      An MCP server that enables AI-powered recipe generation and transformation using natural language, supporting dietary restrictions, allergies, and nutritional goals.
      2
      13 npm
      MIT
    • A
      license
      B
      quality
      D
      maintenance
      MCP server for meal planning and grocery list generation, enabling recipe storage, meal plan creation, and automated grocery lists with ignored ingredients.
      8
      2
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      MCP server that provides cooking recipe lookup, classification, and weekly meal planning based on dietary restrictions and allergies.
      5
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      MCP server that searches French recipes from Marmiton, reads ingredients and steps, and rescales quantities to any number of servings without requiring an API key.
      3
      245 npm
      1
      MIT