mcp-bbc-goodfood
This MCP server lets you browse and search BBC Good Food recipes, read full recipe details (with scaling and unit conversion), and rescale any ingredient list without needing an API key.
List filters: Discover the diet, cuisine, meal type, and difficulty values the site uses, with recipe counts, optionally scoped to a search query.
Search recipes: Find recipes by dish, ingredient, or technique; narrow by diet, cuisine, meal type, difficulty, max time, max calories, min servings, or min rating; sort by relevance, rating, publication date, or quickest; control page size and pagination; exclude subscription-only results.
Read a recipe: Fetch full details for a recipe by its path — ingredients, steps, prep/cook/total times, difficulty, diets, author, rating, description, and nutrition per serving.
Scale recipes: Request a recipe for a specific number of servings; ingredient quantities are recomputed and marked as exact, rounded, or unscaled.
Convert units: Read recipes in metric or US units.
Scale arbitrary ingredient lists: Multiply or convert any provided ingredient lines by a factor or from/to serving counts, with no request to the site.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-bbc-goodfoodShow me the available diet filters for chicken recipes"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-bbc-goodfood
BBC Good Food is a British cooking site, the online home of the magazine of the same name. Its recipes are written and tested by its own cooks, and each one gives its ingredients, its method, its preparation and cooking times, its difficulty, the diets it suits, its nutrition per serving and the stars its readers gave it. The site narrows its recipes along axes of its own: a diet, a cuisine, a kind of meal, a difficulty. Part of the collection sits behind a subscription.
This server connects a chat client to that site. You can read the values each axis takes, search the recipes along them, read one recipe with its ingredients rescaled to the number of people at your table, and switch its quantities between metric and US units. It needs no API key and no account.
Install
One-click install
Claude Code
claude mcp add bbc-goodfood -- npx -y mcp-bbc-goodfoodClaude Desktop, Cursor, and any client using the standard config format
{
"mcpServers": {
"bbc-goodfood": {
"command": "npx",
"args": ["-y", "mcp-bbc-goodfood"]
}
}
}Node 24 or later is required, and no environment variable has to be set.
With Docker
{
"mcpServers": {
"bbc-goodfood": {
"command": "docker",
"args": ["run", "-i", "--rm", "ghcr.io/smeet666/mcp-bbc-goodfood:1.1.0"]
}
}
}-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.bbcgoodfood.com, and nothing else: no volume, no port, no credential.
Bundle, without npm
Download mcp-bbc-goodfood-1.1.0.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: mcp-cookbook
What you can ask
"Find me a vegetarian curry that takes under 40 minutes."
"What diets can I filter on?"
"Read me that recipe for six, in US cups."
"Which of these are rated four stars or better?"
"Scale this ingredient list from a magazine by 1.5."
The ordinary path runs list_filters, then search_recipes, then get_recipe
on the path a row carries.
Tools
Tool | What it does |
| Reads the values each axis of the site takes. |
| Finds recipes, narrowed along those axes. |
| Reads one recipe, rescaled or in other units on request. |
| Rescales any ingredient list, with no request to the site. |
Call list_filters before narrowing a search. The site accepts any value on
an axis and answers one it does not know with a total of zero, so a guessed
spelling comes back as a confident absence instead of a refusal.
list_filters
Reads the axes the site narrows by, and the values each one takes.
Argument | Type | Required | What it does |
| string, 1 to 80 characters | no | Count the values within one search instead of across the whole listing. |
In return: filters, one entry per axis carrying name and label in the
site's own wording, argument, which names the argument search_recipes takes
for it, and options with each value, its label and its count. A count
the site published nothing for is null. option_count says how many options are
listed here, which is fewer than the site accepts: the values returned are the
most frequent ones, and an option absent from the list is still usable. Counts
are measured inside a scope, so passing query counts within one search and
leaving it out counts across the listing; the two answer different questions.
search_recipes
Searches the recipes, narrowed along the site's own axes and along restrictions this server applies to the rows it read.
Argument | Type | Required | What it does |
| string, 1 to 80 characters | yes | A dish, an ingredient, a technique. |
| integer, 1 to 30, default | no | Rows to serve. |
| integer, 1 to 334, default | no | Which page of rows. |
|
| no | How the site orders the rows. |
| string, 1 to 60 characters | no | A value |
| string, 1 to 60 characters | no | A value |
| string, 1 to 60 characters | no | A value |
| string, 1 to 60 characters | no | A value |
| integer, 1 to 1440 | no | The whole recipe, in minutes. |
| integer, 1 to 10000 | no | Calories per serving. |
| integer, 1 to 50 | no | At least this many servings. |
| number, 1 to 5 | no | At least this many stars. |
| boolean | no | Drop the rows behind the site's subscription. |
In return: rows carrying id, which get_recipe takes; title; url;
image_url; and rating, which is null where the site published none.
Alongside come result_count, rows_seen for the rows the site served before
anything was set aside, and total_available. A total marked total_is_ceiling
sits on the largest number of rows one search will serve, so it states a floor
rather than a count. restrictions_lifted names what was set aside when
narrowing made the search fail, and premium_dropped counts the subscription
rows removed. The site offers no restriction on subscription rows, so
exclude_premium removes them after the page arrives: a page then comes back
shorter than the limit asked for, and a short page is not the end of the results.
get_recipe
Reads one recipe, rescaled to a number of servings and in the unit system asked for.
Argument | Type | Required | What it does |
| string, 1 to 200 characters | yes | The page's own path, as a |
| integer, 1 to 100 | no | Rescale the ingredients to this many servings. |
|
| no | The units the quantities are written in. |
In return: title, url, premium, yield_text in the site's own wording
such as Serves 4 - 6, yield_count, prep_minutes, cook_minutes,
total_minutes, difficulty, diets, author, rating, rating_count,
description, ingredients, steps, nutrition with nutrition_per naming
the serving it describes, and unit_system. A figure the page states nothing for
is null. A recipe behind the site's subscription comes back with premium
true, no ingredients and no steps: send the reader to its page rather than
reconstructing them. Each ingredient carries scaling, reading scaled,
rounded or unscaled.
scale_ingredients
Applies the same arithmetic to any list of ingredient lines, with no request to the site.
Argument | Type | Required | What it does |
| array of 1 to 100 strings, 1 to 300 characters | yes | The lines to rescale, as a recipe writes them. |
| number, 0.001 to 1000 | one of two | What to multiply every quantity by. |
| integer, 1 to 100 | one of two | How many people the list feeds as written. |
| integer, 1 to 100 | one of two | How many people it should feed. |
Pass factor, or the from_servings and to_servings pair.
In return: the rescaled lines in the shape get_recipe returns, each with its
original, its text, its amount, amount_max and unit, and 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, and 2 g divided by ten reads 200 mg.
How finely an ingredient can be divided depends on what it is. A loaf 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 figures are this server's arithmetic, so say they were recomputed when you show them. A recipe whose page states no number of servings cannot be put to a number of people, and the answer says so.
Configuration
Every variable is optional. Set them in the env block of your client config.
Variable | Default | What it does |
| the project identity | Names your application to the site, with an address where a person can be reached. |
|
| Gap between two requests, from 1000 to 60000. |
|
| Deadline for one request, from 1000 to 120000. |
|
| Attempts after a transient failure, from 0 to 8. |
|
| How long a page stays in memory, from 0 to 86400000. |
|
| Pages held in memory at once, from 1 to 5000. |
|
| Largest page this reads, in bytes, from 100000 to 64000000. |
|
|
|
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 |
| The site answered, and holds no such recipe. | Check the path with |
| The arguments were refused before any request went out. | Read the message, which names the argument. |
| The site asked this client to slow down. | Wait the number of seconds the hint names and call again with the same arguments. The recipe is still there. |
| The page loaded and the expected content was absent. | Report it at the issue tracker. |
| The request did not complete. | Try again shortly. |
| The request passed its deadline. | Raise |
As a library
The layer reading the site is published on its own, with its pacing, its cache and its errors, and with no protocol attached.
import { BbcGoodFoodClient } from "mcp-bbc-goodfood/client";
const client = new BbcGoodFoodClient();
const { data, cached } = await client.searchRecipes({ query: "lasagne" });
console.log(data.rows.length, cached);listFilters, searchRecipes and getRecipe each answer { data, cached },
and throw an error carrying one of the six codes. The floor between two requests
holds here as well.
Pacing and attribution
Requests go out one at a time with at least a second and a half between them, and
the floor of one second holds however the server is configured. The User-Agent
always ends with the project identity and an address where a person can be
reached.
Every result carries the address of the page it was read from, and source names
the site. The recipes belong to BBC Good Food and to the cooks who wrote them.
This MCP server is an unofficial project, with no affiliation to BBC Good Food.
Privacy
This server collects nothing about you and sends nothing to its author. It runs
on your machine, contacts www.bbcgoodfood.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 checkTests 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
site itself.
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 BBC Good Food and to their authors.
mcp-bbc-goodfood (français)
BBC Good Food est un site de cuisine britannique, la maison en ligne du magazine du même nom. Ses recettes sont écrites et testées par ses propres cuisiniers, et chacune donne ses ingrédients, sa méthode, ses temps de préparation et de cuisson, sa difficulté, les régimes auxquels elle convient, ses valeurs nutritionnelles par portion et les étoiles que ses lecteurs lui ont données. Le site resserre ses recettes selon des axes qui lui sont propres : un régime, une cuisine, un type de repas, une difficulté. Une partie de la collection est réservée aux abonnés.
Ce serveur relie un client de conversation à ce site. On peut lire les valeurs que prend chaque axe, chercher des recettes le long de ces axes, lire une recette avec ses ingrédients adaptés au nombre de convives, et basculer ses quantités entre unités métriques et américaines. Aucune clé d'API, aucun compte.
Installation
Installation en un clic
Claude Code
claude mcp add bbc-goodfood -- npx -y mcp-bbc-goodfoodClaude Desktop, Cursor, et tout client au format de configuration standard
{
"mcpServers": {
"bbc-goodfood": {
"command": "npx",
"args": ["-y", "mcp-bbc-goodfood"]
}
}
}Node 24 ou plus récent est nécessaire, et aucune variable d'environnement n'est à renseigner.
Avec Docker
{
"mcpServers": {
"bbc-goodfood": {
"command": "docker",
"args": ["run", "-i", "--rm", "ghcr.io/smeet666/mcp-bbc-goodfood:1.1.0"]
}
}
}-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.bbcgoodfood.com, et de rien d'autre : aucun volume, aucun
port, aucun identifiant.
Bundle, sans npm
Téléchargez mcp-bbc-goodfood-1.1.0.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 un curry végétarien qui prend moins de 40 minutes. »
« Sur quels régimes puis-je filtrer ? »
« Lis-moi cette recette pour six, en tasses américaines. »
« Lesquelles sont notées quatre étoiles ou plus ? »
« Multiplie par 1,5 cette liste d'ingrédients tirée d'un magazine. »
Le chemin ordinaire va de list_filters à search_recipes, puis à get_recipe
sur le chemin que porte une ligne.
Les outils
Outil | Ce qu'il fait |
| Lit les valeurs que prend chaque axe du site. |
| Trouve des recettes, resserrées selon ces axes. |
| Lit une recette, adaptée ou dans d'autres unités sur demande. |
| Adapte n'importe quelle liste d'ingrédients, sans requête au site. |
Appelez list_filters avant de resserrer une recherche. Le site accepte
n'importe quelle valeur sur un axe et répond à celle qu'il ne connaît pas par un
total de zéro, donc une orthographe devinée revient comme une absence assurée au
lieu d'un refus.
list_filters
Lit les axes selon lesquels le site resserre, et les valeurs que chacun prend.
Argument | Type | Requis | Ce qu'il fait |
| chaîne, 1 à 80 caractères | non | Compte les valeurs dans une recherche plutôt que sur toute la liste. |
En retour : filters, une entrée par axe portant name et label dans les
termes du site, argument, qui nomme l'argument que search_recipes prend pour
lui, et options avec chaque value, son label et son count. Un count que
le site n'a pas publié vaut null. option_count dit combien d'options sont
listées ici, ce qui est moins que ce que le site accepte : les valeurs rendues
sont les plus fréquentes, et une option absente de la liste reste utilisable. Les
comptes sont mesurés dans une portée, donc passer query compte dans une
recherche et l'omettre compte sur toute la liste ; les deux répondent à des
questions différentes.
search_recipes
Cherche des recettes, resserrées selon les axes du site et selon des restrictions que ce serveur applique aux lignes qu'il a lues.
Argument | Type | Requis | Ce qu'il fait |
| chaîne, 1 à 80 caractères | oui | Un plat, un ingrédient, une technique. |
| entier, 1 à 30, défaut | non | Lignes à servir. |
| entier, 1 à 334, défaut | non | Quelle page de lignes. |
|
| non | L'ordre dans lequel le site range les lignes. |
| chaîne, 1 à 60 caractères | non | Une valeur publiée par |
| chaîne, 1 à 60 caractères | non | Une valeur publiée par |
| chaîne, 1 à 60 caractères | non | Une valeur publiée par |
| chaîne, 1 à 60 caractères | non | Une valeur publiée par |
| entier, 1 à 1440 | non | La recette entière, en minutes. |
| entier, 1 à 10000 | non | Calories par portion. |
| entier, 1 à 50 | non | Au moins ce nombre de portions. |
| nombre, 1 à 5 | non | Au moins ce nombre d'étoiles. |
| booléen | non | Retire les lignes réservées aux abonnés. |
En retour : des lignes portant id, que get_recipe reprend ; title ;
url ; image_url ; et rating, null là où le site n'en a publié aucune.
Viennent aussi result_count, rows_seen pour les lignes servies par le site
avant tout écartement, et total_available. Un total marqué total_is_ceiling
se pose sur le plus grand nombre de lignes qu'une recherche servira, donc il
énonce un plancher plutôt qu'un compte. restrictions_lifted nomme ce qui a été
écarté quand le resserrement faisait échouer la recherche, et premium_dropped
compte les lignes d'abonnés retirées. Le site n'offre aucune restriction sur les
lignes d'abonnés, donc exclude_premium les retire une fois la page arrivée :
une page revient alors plus courte que la limite demandée, et une page courte
n'est pas la fin des résultats.
get_recipe
Lit une recette, adaptée à un nombre de parts et dans le système d'unités demandé.
Argument | Type | Requis | Ce qu'il fait |
| chaîne, 1 à 200 caractères | oui | Le chemin de la page, tel qu'une ligne le porte. |
| entier, 1 à 100 | non | Adapte les ingrédients à ce nombre de parts. |
|
| non | Les unités dans lesquelles les quantités sont écrites. |
En retour : title, url, premium, yield_text dans les termes du site
comme Serves 4 - 6, yield_count, prep_minutes, cook_minutes,
total_minutes, difficulty, diets, author, rating, rating_count,
description, ingredients, steps, nutrition avec nutrition_per qui nomme
la portion décrite, et unit_system. Un chiffre que la page n'indique pas vaut
null. Une recette réservée aux abonnés revient avec premium à vrai, sans
ingrédients et sans étapes : renvoyez le lecteur vers sa page au lieu de les
reconstituer. Chaque ingrédient porte scaling, valant scaled, rounded ou
unscaled.
scale_ingredients
Applique la même arithmétique à n'importe quelle liste d'ingrédients, sans requête au site.
Argument | Type | Requis | Ce qu'il fait |
| tableau de 1 à 100 chaînes, 1 à 300 caractères | oui | Les lignes à adapter, comme une recette les écrit. |
| nombre, 0.001 à 1000 | l'un des deux | Ce par quoi multiplier chaque quantité. |
| entier, 1 à 100 | l'un des deux | Le nombre de convives de la liste d'origine. |
| entier, 1 à 100 | l'un des deux | Le nombre de convives voulu. |
Passez factor, ou le couple from_servings et to_servings.
En retour : les lignes adaptées dans la forme que rend get_recipe, chacune
avec son original, son text, son amount, amount_max et unit, et son
scaling.
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, et 2 g divisés par dix donnent 200 mg.
La finesse à laquelle un ingrédient se coupe dépend de sa nature. Un pain 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 chiffres sont l'arithmétique de ce serveur, donc dites qu'ils ont été recalculés quand vous les montrez. Une recette dont la page n'indique aucun nombre de parts ne peut pas être portée à un nombre de convives, et la réponse le dit.
Configuration
Chaque variable est facultative. Elles se posent dans le bloc env de la
configuration du client.
Variable | Défaut | Ce qu'elle fait |
| l'identité du projet | Nomme votre application auprès du site, avec une adresse où joindre une personne. |
|
| Écart entre deux requêtes, de 1000 à 60000. |
|
| Délai d'une requête, de 1000 à 120000. |
|
| Tentatives après un échec passager, de 0 à 8. |
|
| Durée pendant laquelle une page reste en mémoire, de 0 à 86400000. |
|
| Pages gardées en mémoire à la fois, de 1 à 5000. |
|
| Plus grande page lue, en octets, de 100000 à 64000000. |
|
|
|
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 |
| Le site a répondu, et n'a pas cette recette. | Vérifiez le chemin avec |
| Les arguments ont été refusés avant toute requête. | Lisez le message, qui nomme l'argument. |
| Le site demande à ce client de ralentir. | Attendez les secondes indiquées et rappelez avec les mêmes arguments. La recette est toujours là. |
| La page a chargé et le contenu attendu est absent. | Signalez-le sur le suivi d'incidents. |
| La requête n'a pas abouti. | Réessayez sous peu. |
| La requête a dépassé son délai. | Augmentez |
Comme bibliothèque
La couche qui lit le site est publiée seule, avec son rythme, son cache et ses erreurs, sans protocole attaché.
import { BbcGoodFoodClient } from "mcp-bbc-goodfood/client";
const client = new BbcGoodFoodClient();
const { data, cached } = await client.searchRecipes({ query: "lasagne" });
console.log(data.rows.length, cached);listFilters, searchRecipes et getRecipe répondent chacun { data, cached },
et lèvent une erreur portant un des six codes. Le plancher entre deux requêtes
tient également ici.
Rythme et attribution
Les requêtes partent une à une avec au moins une seconde et demie entre elles, et
le plancher d'une seconde tient quelle que soit la configuration. Le User-Agent
se termine toujours par l'identité du projet et une adresse où joindre une
personne.
Chaque résultat porte l'adresse de la page d'où il a été lu, et source nomme le
site. Les recettes appartiennent à BBC Good Food et aux cuisiniers qui les ont
écrites.
Ce MCP est un projet non officiel, sans affiliation à BBC Good Food.
Confidentialité
Ce serveur ne collecte rien sur vous et n'envoie rien à son auteur. Il tourne sur
votre machine, ne joint que www.bbcgoodfood.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 checkLes 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 le site lui-même.
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 à BBC Good Food et à leurs auteurs.
Available Tools
4 toolsget_recipeRead a recipeARead-onlyIdempotent
Read one recipe on BBC Good Food: its ingredients, its steps, its times, its rating and its nutrition. Pass the 'id' a search_recipes row carries, which is the page's own path. A recipe behind the site's subscription comes back with everything except its ingredients and steps, and says so: its page on the site is where a subscriber reads it. The site writes many of its recipes twice, once for its own readers and once restated for readers in the United States, and 'unit_system' chooses which of the two to read.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The page's own path, as a search_recipes row carries it. | |
| servings | No | Put the ingredients to this many people. Quantities are then recomputed by this server, not published by the site, and each line says so under 'scaling'. | |
| unit_system | No | Which of the site's own two renditions to read: 'metric' as it writes for its own readers, 'us' as it restates for readers in the United States. Both are the site's words. A recipe it restated nowhere comes back as it published it, said in 'unit_system' and in the notes. |
Output Schema
| Name | Required | Description |
|---|---|---|
| id | Yes | |
| url | Yes | The page. Show this when citing the recipe. |
| diets | Yes | |
| notes | Yes | |
| steps | Yes | Empty when the recipe sits behind the site's subscription. |
| title | Yes | |
| yield | Yes | What the ingredients were put to, and what they were put from. |
| author | Yes | |
| rating | Yes | 1 to 5. Null when nobody has rated it. |
| source | Yes | |
| premium | Yes | True when the recipe sits behind the site's subscription. |
| nutrition | Yes | |
| difficulty | Yes | |
| yield_text | Yes | The site's own wording, such as 'Serves 4 - 6'. |
| description | Yes | |
| ingredients | Yes | Empty when the recipe sits behind the site's subscription. |
| unit_system | Yes | Which of the site's two renditions this answer carries. |
| yield_count | Yes | The first whole number of that wording. |
| cook_minutes | Yes | |
| prep_minutes | Yes | |
| rating_count | Yes | |
| nutrition_per | Yes | The site's own wording for the serving. |
| total_minutes | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnly/idempotent annotations, the description reveals that subscription recipes omit ingredients and steps but explicitly say so, and that many recipes exist in two regional renditions selected by unit_system. This is meaningful behavioral context that annotations alone don't provide.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences, all informative, with the core purpose front-loaded. No redundant filler; each clause earns its place, including the paywall caveat and regional variant explanation.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a single-recipe read operation with a full output schema and strong annotations, the description covers the key edge cases (paywall, regional variants) and the id provenance. Nothing essential for calling it correctly is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already documents all three parameters in detail (100% coverage), including id's source and unit_system's meaning. The description adds no new parameter-level detail beyond restating id's origin and unit_system's role, so a baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb ('Read') and resource ('one recipe on BBC Good Food') and enumerates the data fields returned (ingredients, steps, times, rating, nutrition). It clearly differentiates from siblings by focusing on a single recipe rather than searching, filtering, or scaling.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly tells the agent to pass the 'id' that a search_recipes row carries, anchoring this tool to the search workflow. It also explains the subscription edge case and the unit_system choice, giving context for when these options matter, though it doesn't list explicit exclusions vs siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
list_filtersList the ways a search can be narrowedARead-onlyIdempotent
List the axes a recipe search can be narrowed along on BBC Good Food, with the values each one takes and how many recipes carry them. Pass 'query' to measure the counts inside one search, or leave it out for the site's whole listing. Read this before narrowing a search: the site accepts any value on a facet and answers one it does not know with a total of zero, so a guessed spelling comes back as a confident absence. The values listed are an excerpt of the most frequent ones, and the site accepts others that are not shown.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | A search to measure the counts inside. The site counts its facets over the rows a search returns, so a count without a query describes the whole listing instead. |
Output Schema
| Name | Required | Description |
|---|---|---|
| notes | Yes | |
| query | Yes | The search the counts were measured in, trimmed. |
| source | Yes | |
| filters | Yes | |
| filter_count | Yes | |
| total_available | Yes | Recipes the site says this scope holds. Null when it published no figure. |
| total_is_ceiling | Yes | True when the total sits on the largest number of rows one search will serve, so it states a floor rather than a count. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, and the description adds meaningful behavioral detail beyond that: the site returns zero for any unknown facet value, so a guessed spelling looks like a confident absence. It also discloses that the listed values are only an excerpt and other values are accepted, which is important practical information.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is four sentences, front-loaded with the core behavior and followed by the important open-world caveat and excerpt warning. Every sentence earns its place, and there is no filler or repeated schema content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With one optional parameter, a rich schema description, an output schema, and annotations, the description covers what an agent needs: how to scope the counts, the fact that counts are measured over search results, and the open-world behavior. There are no obvious gaps that would prevent correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage for the single query parameter is 100%, so the schema already explains that counts without a query describe the whole listing. The description restates this idea but does not add much meaning beyond the schema, so a baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific action and resource: listing the axes a recipe search can be narrowed along on BBC Good Food, including values and recipe counts. This clearly distinguishes it from the sibling tools such as search_recipes because it is about enumerating facets rather than performing a search or fetching a recipe.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives clear context by saying to read this before narrowing a search, and it explains how to get counts for a specific query versus the whole listing. It does not explicitly name search_recipes as the execution alternative, but the sequencing guidance and facet-counting behavior make the intended use obvious.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
scale_ingredientsScale a list of ingredientsARead-onlyIdempotent
Put a list of ingredient lines to a different number of people. Pass 'factor', or else the pair 'from_servings' and 'to_servings'. Quantities are recomputed by this server and not by the site, and every line says under 'scaling' whether the arithmetic landed exactly, whether the figure was moved to stay usable in a kitchen, or whether the line carried nothing to multiply.
| Name | Required | Description | Default |
|---|---|---|---|
| factor | No | What to multiply every quantity by. Pass this or the servings pair, never both. | |
| ingredients | Yes | The lines to scale, as a recipe writes them, such as '200g plain flour'. | |
| to_servings | No | How many people it should feed. | |
| from_servings | No | How many people the list feeds as written. |
Output Schema
| Name | Required | Description |
|---|---|---|
| notes | Yes | |
| factor | Yes | What every quantity was multiplied by. |
| source | Yes | |
| ingredients | Yes | |
| scaled_count | Yes | Lines whose arithmetic landed exactly. |
| rounded_count | Yes | Lines whose figure was moved. |
| unscaled_count | Yes | Lines that carried no quantity to multiply. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description goes beyond the annotations by revealing that quantities are recomputed server-side, not by the website, and explains what each ingredient line will state under 'scaling'. This tells the caller what to expect and that the operation is non-destructive and idempotent. This aligns with the readOnly/idempotent annotations without contradicting them.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is relatively brief and field-oriented. It leads with the primary purpose, covers the parameter modes, and includes the useful scaling behavior. The sentence about scaling statuses is a bit long, but it earns its place because it describes what to expect in the output.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is sufficient for an agent to know when to use the tool, which keys to pass, and what the output will say about each line. Combined with an output schema, full parameter schema coverage, and annotations, no critical behavioral details are missing for safe and correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already provides descriptions for all 4 parameters, so the baseline is adequate. The description adds value by explaining the mutually exclusive relationship between 'factor' and the servings pair, something the schema alone does not emphasize. It also gives semantic meaning to the scaling status output without repeating schema details.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a strong verb and resource: it scales a list of ingredient lines to a different number of people. It also distinguishes the tool's operation from the siblings (search, listing, fetching) by naming the computation mode. The added detail about 'factor' or 'servings pair' makes the purpose precise.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains exactly how the tool should be invoked: pass 'factor' or the 'from_servings'/'to_servings' pair. It clearly communicates the mutually exclusive parameter use. It does not explicitly discuss when to use this tool versus the siblings, but the tool's purpose is sufficiently distinct for an agent to select it without deep inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search_recipesSearch recipesARead-onlyIdempotent
Search recipes on BBC Good Food and return a listing. Narrow it with 'diet', 'cuisine', 'meal_type', 'difficulty' or a bound such as 'max_total_minutes'; call list_filters first for the values each one takes, since the site answers a value it does not know with a count of zero. The site ranks rather than filters: it answers a term it holds nothing for with rows all the same, so read the titles rather than trusting the count. Each row carries the page to read the recipe on.
| Name | Required | Description | Default |
|---|---|---|---|
| diet | No | A value list_filters publishes. | |
| page | No | Which page of rows. Default 1. | |
| sort | No | How the site orders the rows. Default 'relevant'. | |
| limit | No | Rows to return. Default 30. | |
| query | Yes | A dish, an ingredient, a technique. | |
| cuisine | No | A value list_filters publishes. | |
| meal_type | No | A value list_filters publishes. | |
| difficulty | No | A value list_filters publishes. | |
| min_rating | No | At least this many stars, 1 to 5. | |
| max_calories | No | Per serving. | |
| min_servings | No | At least this many servings. | |
| exclude_premium | No | Drop the rows that sit behind the site's subscription. The site offers no such restriction, so the rows are removed from the page after it arrives: a page comes back shorter than the limit asked for, and a short page is not the end of the results. | |
| max_total_minutes | No | Whole recipe, minutes. |
Output Schema
| Name | Required | Description |
|---|---|---|
| notes | Yes | |
| query | Yes | |
| source | Yes | |
| results | Yes | |
| rows_seen | Yes | Rows the site served, before anything was set aside. |
| result_count | Yes | Rows rendered, after anything unreadable was set aside. |
| premium_dropped | Yes | Rows removed from this page for sitting behind the site's subscription. |
| total_available | Yes | Recipes the site says the search holds. |
| total_is_ceiling | Yes | True when the total sits on the most rows one search will serve, so it states a floor. |
| restrictions_lifted | Yes | Restrictions let go of so the search could run again after the restricted one returned nothing. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnly/idempotent annotations, it discloses that the site ranks rather than filters, that unknown terms produce identical rows rather than reliable counts, and that each row carries the page to read the recipe on. These are non-obvious behaviors an agent needs to interpret results correctly.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is dense but every sentence contributes: scope, filtering guidance, result-interpretation warning, and page-link follow-up. It is front-loaded with the core purpose and wastes no words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With an output schema present and annotations covering read-only, idempotent, and non-destructive behavior, the description covers the remaining operational caveats: filter-value lookup, ranking semantics, and the meaning of rows. Nothing needed to call the tool correctly is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description adds little parameter-level meaning beyond pointing to list_filters for filter values and highlighting max_total_minutes as a bound, both of which the schema already covers.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb and resource: 'Search recipes on BBC Good Food and return a listing.' It distinguishes itself from list_filters by explicitly instructing to call list_filters first, and from get_recipe by framing the output as a listing whose rows carry the page for reading the recipe.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It gives explicit usage guidance: call list_filters first for filter values and warns that unknown values return zero counts. It does not explicitly name get_recipe as the alternative for reading a single recipe, though the closing sentence implies that follow-up.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
4 tool updates
v1.1.0- Changed
get_recipe23 fields changed- removed
Output schema / properties / author / anyOfRemoved value: -[ - { - "type": "string" - }, - { - "type": "null" - } -] - added
Output schema / properties / author / typeAdded value: +[ + "string", + "null" +] - removed
Output schema / properties / description / anyOfRemoved value: -[ - { - "type": "string" - }, - { - "type": "null" - } -] - added
Output schema / properties / description / typeAdded value: +[ + "string", + "null" +] - removed
Output schema / properties / difficulty / anyOfRemoved value: -[ - { - "type": "string" - }, - { - "type": "null" - } -] - added
Output schema / properties / difficulty / typeAdded value: +[ + "string", + "null" +] - removed
Output schema / properties / ingredients / items / properties / heading / anyOfRemoved value: -[ - { - "type": "string" - }, - { - "type": "null" - } -] - added
Output schema / properties / ingredients / items / properties / heading / typeAdded value: +[ + "string", + "null" +] - changed
Output schema / properties / ingredients / items / properties / ingredients / items / anyOfPrevious value: -[ - { - "additionalProperties": false, - "properties": { - "amount": { - "anyOf": [ - { - "type": "number" - }, - { - "type": "null" - } - ], - "description": "Null when the site states no quantity." - }, - "item": { - "description": "What goes in, without its quantity.", - "type": "string" - }, - "note": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "description": "What to do to it beforehand, such as 'thinly sliced'." - }, - "term": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ], - "description": "The site's own normalised name for it." - }, - "text": { - "description": "The line as the site composes it.", - "type": "string" - }, - "unit": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ] - } - }, - "required": [ - "text", - "amount", - "unit", - "item", - "note", - "term" - ], - "type": "object" - }, - { - "additionalProperties": false, - "properties": { - "amount": { - "anyOf": [ - { - "type": "number" - }, - { - "type": "null" - } - ] - }, - "amount_max": { - "anyOf": [ - { - "type": "number" - }, - { - "type": "null" - } - ] - }, - "original": { - "description": "The line as the site composes it.", - "type": "string" - }, - "scaling": { - "description": "'scaled': the arithmetic landed exactly. 'rounded': the figure moved to stay usable in a kitchen. 'unscaled': the line carried no quantity.", - "enum": [ - "scaled", - "rounded", - "unscaled" - ], - "type": "string" - }, - "text": { - "description": "The line as it now reads.", - "type": "string" - }, - "unit": { - "anyOf": [ - { - "type": "string" - }, - { - "type": "null" - } - ] - } - }, - "required": [ - "text", - "original", - "scaling", - "amount", - "amount_max", - "unit" - ], - "type": "object" - } -]New value: +[ + { + "additionalProperties": false, + "properties": { + "amount": { + "description": "Null when the site states no quantity.", + "type": [ + "number", + "null" + ] + }, + "item": { + "description": "What goes in, without its quantity.", + "type": "string" + }, + "note": { + "description": "What to do to it beforehand, such as 'thinly sliced'.", + "type": [ + "string", + "null" + ] + }, + "term": { + "description": "The site's own normalised name for it.", + "type": [ + "string", + "null" + ] + }, + "text": { + "description": "The line as the site composes it.", + "type": "string" + }, + "unit": { + "type": [ + "string", + "null" + ] + } + }, + "required": [ + "text", + "amount", + "unit", + "item", + "note", + "term" + ], + "type": "object" + }, + { + "additionalProperties": false, + "properties": { + "amount": { + "type": [ + "number", + "null" + ] + }, + "amount_max": { + "type": [ + "number", + "null" + ] + }, + "original": { + "description": "The line as the site composes it.", + "type": "string" + }, + "scaling": { + "description": "'scaled': the arithmetic landed exactly. 'rounded': the figure moved to stay usable in a kitchen. 'unscaled': the line carried no quantity.", + "enum": [ + "scaled", + "rounded", + "unscaled" + ], + "type": "string" + }, + "text": { + "description": "The line as it now reads.", + "type": "string" + }, + "unit": { + "type": [ + "string", + "null" + ] + } + }, + "required": [ + "text", + "original", + "scaling", + "amount", + "amount_max", + "unit" + ], + "type": "object" + } +] - removed
Output schema / properties / nutrition / items / properties / value / anyOfRemoved value: -[ - { - "type": "number" - }, - { - "type": "null" - } -] - added
Output schema / properties / nutrition / items / properties / value / typeAdded value: +[ + "number", + "null" +] - removed
Output schema / properties / nutrition_per / anyOfRemoved value: -[ - { - "type": "string" - }, - { - "type": "null" - } -] - added
Output schema / properties / nutrition_per / typeAdded value: +[ + "string", + "null" +] - removed
Output schema / properties / rating / anyOfRemoved value: -[ - { - "type": "number" - }, - { - "type": "null" - } -] - added
Output schema / properties / rating / typeAdded value: +[ + "number", + "null" +] - removed
Output schema / properties / yield / properties / factor / anyOfRemoved value: -[ - { - "type": "number" - }, - { - "type": "null" - } -] - added
Output schema / properties / yield / properties / factor / typeAdded value: +[ + "number", + "null" +] - removed
Output schema / properties / yield / properties / original_text / anyOfRemoved value: -[ - { - "type": "string" - }, - { - "type": "null" - } -] - added
Output schema / properties / yield / properties / original_text / typeAdded value: +[ + "string", + "null" +] - removed
Output schema / properties / yield / properties / unit / anyOfRemoved value: -[ - { - "type": "string" - }, - { - "type": "null" - } -] - added
Output schema / properties / yield / properties / unit / typeAdded value: +[ + "string", + "null" +] - removed
Output schema / properties / yield_text / anyOfRemoved value: -[ - { - "type": "string" - }, - { - "type": "null" - } -] - added
Output schema / properties / yield_text / typeAdded value: +[ + "string", + "null" +]
- Changed
list_filters4 fields changed- removed
Output schema / properties / filters / items / properties / argument / anyOfRemoved value: -[ - { - "type": "string" - }, - { - "type": "null" - } -] - added
Output schema / properties / filters / items / properties / argument / typeAdded value: +[ + "string", + "null" +] - removed
Output schema / properties / query / anyOfRemoved value: -[ - { - "type": "string" - }, - { - "type": "null" - } -] - added
Output schema / properties / query / typeAdded value: +[ + "string", + "null" +]
- Changed
scale_ingredients6 fields changed- removed
Output schema / properties / ingredients / items / properties / amount / anyOfRemoved value: -[ - { - "type": "number" - }, - { - "type": "null" - } -] - added
Output schema / properties / ingredients / items / properties / amount / typeAdded value: +[ + "number", + "null" +] - removed
Output schema / properties / ingredients / items / properties / amount_max / anyOfRemoved value: -[ - { - "type": "number" - }, - { - "type": "null" - } -] - added
Output schema / properties / ingredients / items / properties / amount_max / typeAdded value: +[ + "number", + "null" +] - removed
Output schema / properties / ingredients / items / properties / unit / anyOfRemoved value: -[ - { - "type": "string" - }, - { - "type": "null" - } -] - added
Output schema / properties / ingredients / items / properties / unit / typeAdded value: +[ + "string", + "null" +]
- Changed
search_recipes8 fields changed- removed
Output schema / properties / results / items / properties / author / anyOfRemoved value: -[ - { - "type": "string" - }, - { - "type": "null" - } -] - added
Output schema / properties / results / items / properties / author / typeAdded value: +[ + "string", + "null" +] - removed
Output schema / properties / results / items / properties / difficulty / anyOfRemoved value: -[ - { - "type": "string" - }, - { - "type": "null" - } -] - added
Output schema / properties / results / items / properties / difficulty / typeAdded value: +[ + "string", + "null" +] - removed
Output schema / properties / results / items / properties / image_url / anyOfRemoved value: -[ - { - "type": "string" - }, - { - "type": "null" - } -] - added
Output schema / properties / results / items / properties / image_url / typeAdded value: +[ + "string", + "null" +] - removed
Output schema / properties / results / items / properties / rating / anyOfRemoved value: -[ - { - "type": "number" - }, - { - "type": "null" - } -] - added
Output schema / properties / results / items / properties / rating / typeAdded value: +[ + "number", + "null" +]
4 tool updates
- Added
get_recipe - Changed
list_filters4 fields changed- added
Output schema / properties / filters / items / properties / argumentAdded value: +{ + "anyOf": [ + { + "type": "string" + }, + { + "type": "null" + } + ], + "description": "The search_recipes argument that restricts this axis. Null where a search takes none. A value listed here is in the site's units and may need converting before it is passed." +} - changed
Output schema / properties / filters / items / properties / name / descriptionPrevious value: -"The argument name a search takes for this axis."New value: +"The site's own name for the axis." - changed
Output schema / properties / filters / items / properties / options / items / properties / value / descriptionPrevious value: -"Pass this back to narrow a search along this axis."New value: +"The value as the site publishes it, in the site's own units." - changed
Output schema / properties / filters / items / requiredPrevious value: -[ - "name", - "label", - "options", - "option_count" -]New value: +[ + "name", + "label", + "argument", + "options", + "option_count" +]
- Added
scale_ingredients - Changed
search_recipes4 fields changed- removed
Output schema / properties / restrictions_droppedRemoved value: -{ - "description": "Restrictions the site could not answer, dropped so the search could run.", - "items": { - "type": "string" - }, - "type": "array" -} - added
Output schema / properties / restrictions_liftedAdded value: +{ + "description": "Restrictions let go of so the search could run again after the restricted one returned nothing.", + "items": { + "type": "string" + }, + "type": "array" +} - changed
Output schema / properties / results / items / properties / id / descriptionPrevious value: -"Opaque to a caller. The site's own identifier for the recipe."New value: +"The page's own path. Pass it to get_recipe to read the recipe." - changed
Output schema / requiredPrevious value: -[ - "query", - "results", - "result_count", - "total_available", - "total_is_ceiling", - "rows_seen", - "restrictions_dropped", - "premium_dropped", - "source", - "notes" -]New value: +[ + "query", + "results", + "result_count", + "total_available", + "total_is_ceiling", + "rows_seen", + "restrictions_lifted", + "premium_dropped", + "source", + "notes" +]
2 tool updates
v0.1.0- First observed
list_filters - First observed
search_recipes
TDQS
Scored across 4 tools
Each tool serves a distinct function: list_filters discovers search axes, search_recipes performs the actual search, get_recipe retrieves details, and scale_ingredients transforms ingredient quantities. There is no overlap in purpose; the dependency between list_filters and search_recipes is clear and complementary.
All tool names follow a consistent verb_noun pattern in snake_case (list_filters, search_recipes, get_recipe, scale_ingredients). The verbs and nouns are specific and predictable, matching the domain perfectly.
Four tools are appropriate for a recipe-focused server. They cover the essential operations without redundancy or bloat, and the scope is well-defined for browsing, searching, and retrieving recipe content.
The tool surface covers the full user workflow for a read-only recipe service: discovering available filters, searching, viewing a recipe, and scaling ingredients. No critical operations are missing for the stated purpose, and the added scaling feature enhances usability without leaving gaps.
Maintenance
Related MCP Connectors
Spoonacular food API: recipes, nutrition, ingredients, meal plans. Free 150/day.
Search and compare attributed recipe records through a public read-only remote MCP endpoint.
Recipes MCP — wraps TheMealDB API (free tier, no auth)
Canadian grocery flyer deals and recipes by item, store, postal code, cuisine, or diet. No auth.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceProvides access to the Spoonacular food API for recipes, nutrition, ingredients, and meal plans.MIT
- FlicenseNot gradedqualityDmaintenanceEnables browsing recipes, searching by category, and viewing detailed recipe information from the Gousto cookbook API via natural language.-
- AlicenseNot gradedqualityCmaintenanceEnables querying Open Food Facts product database by barcode, full-text search, category, brand, or country.5 npmMIT

MealCP MCPofficial
AlicenseAqualityAmaintenanceEnables searching grocery product catalogs with faceted filters and retrieving price history statistics via the MealCP grocery price API.2MIT