de en es ja ko ru zh

mcp-bbc-goodfood

Name: mcp-bbc-goodfood
Author: smeet666

by smeet666

Overview Schema Source Related Servers Discussions Admin

TypeScript

Remote

mcp-bbc-goodfood

npm licence MIT

Ein MCP-Server, der Rezepte auf BBC Good Food liest. Nur lesend, ohne API-Schlüssel, ohne Konto.

Französische Version

Warum es das gibt

BBC Good Food akzeptiert jeden Wert auf einer Suchfacette und antwortet auf einen unbekannten Wert mit einer Gesamtzahl von null. Fragt man nach glutenfree statt gluten-free, sagt die Seite, dass nichts übereinstimmt, mit derselben Sicherheit, mit der sie sagt, dass 48 Rezepte zur korrekten Schreibweise passen. Ein Modell, das eine Schreibweise errät, erhält eine selbstbewusste Abwesenheit statt einer Ablehnung.

Dieser Server veröffentlicht das Vokabular, damit die Frage richtig gestellt werden kann.

Related MCP server: mcp-cookbook

Das Werkzeug

`list_filters`

Listet die Achsen auf, entlang derer eine Rezeptsuche eingegrenzt werden kann, mit den Werten, die jede annimmt, und wie viele Rezepte sie tragen.

Argument	Typ	Bedeutung
`query`	Zeichenkette, optional	Misst die Zählungen innerhalb dieser Suche. Ohne ihn gilt das gesamte Verzeichnis der Seite.

Die Seite zählt ihre Facetten über die Zeilen, die eine Suche zurückgibt, also beantworten die beiden verschiedene Fragen. Innerhalb von chicken meldet diet gluten-free 48. Über das gesamte Verzeichnis meldet es gluten-free 2810. Keines ist mit dem anderen vergleichbar, und die Antwort sagt, welchen Umfang sie gemessen hat.

{
  "query": "chicken",
  "filters": [
    {
      "name": "diet",
      "label": "Diets",
      "options": [{ "value": "gluten-free", "label": "Gluten-free", "count": 48 }],
      "option_count": 10
    }
  ],
  "filter_count": 9,
  "total_available": 363,
  "total_is_ceiling": false,
  "rows_seen": 30,
  "matched_rows": 30,
  "source": "BBC Good Food",
  "notes": ["…"]
}

Was die Antworten nicht überbewerten

Die veröffentlichten Werte sind eine Auswahlliste. Die Seite zeigt die zehn häufigsten Werte auf einer Achse und akzeptiert andere, die sie nie auflistet: cuisine=mexican grenzt eine Suche auf 306 Rezepte ein, ohne unter den zehn zu erscheinen. Die Antwort sagt, dass die Liste ein Auszug ist, statt sie die Menge der akzeptierten Werte zu nennen, denn ein Server, der sie so nennen würde, würde Werte ablehnen, die funktionieren.

Eine Gesamtzahl kann eine Untergrenze sein. Die Seite liefert höchstens 10 000 Zeilen für eine Suche und hört dort auf. Eine Gesamtzahl, die genau auf diese Zahl fällt, wurde abgeschnitten, also nennt sie eine Untergrenze statt einer Zählung, und total_is_ceiling sagt das.

Eine Zählung, für die die Seite nichts veröffentlicht hat, ist null, nie 0. Auf einer Skala, die bei null beginnt, wären die beiden nicht zu unterscheiden.

Die Seite beantwortet einen Begriff, für den sie nichts hat, mit Zeilen, die alle gleich sind. Die Suche nach foobar liefert sieben Rezepte — darunter einen Rhabarber-Fizz und einen Flapjack-Riegel —, die über Fragmente abgeglichen wurden, ohne dass etwas die Antwort als Fehlschlag kennzeichnet. Jede Antwort meldet daher rows_seen und matched_rows: wie viele Zeilen die Seite geliefert hat und wie viele davon ein Wort der Suche tragen. Wenn die zweite null ist und die erste nicht, sagt eine Anmerkung, dass die Zählung beschreibt, was die Seite angeboten hat, statt was übereinstimmte.

Zwei Zählungen statt eines Urteils. Eine legitime Suche kann in keinem Titel vorkommen, und ein Leser, der 2 von 30 sieht, urteilt besser als eine Markierung, die für ihn urteilt.

Installation

npx mcp-bbc-goodfood

Claude Code

claude mcp add bbc-goodfood -- npx -y mcp-bbc-goodfood

Jeder MCP-Client

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

Container

docker build -t mcp-bbc-goodfood .
docker run -i --rm mcp-bbc-goodfood

Der Container muss www.bbcgoodfood.com erreichen können und sonst nichts. Er nimmt keine Anmeldedaten entgegen, weil es keine zu nehmen gibt.

Einstellungen

Jede Einstellung ist eine Umgebungsvariable, und keine ist erforderlich. Ein Wert außerhalb seines Bereichs wird mit einer Zeile auf stderr abgelehnt, und der Standardwert bleibt bestehen: Eine Einstellung, die nicht wirksam werden kann, sagt das, statt stillschweigend begrenzt zu werden.

Variable	Standard	Bereich
`BGF_USER_AGENT`	—	Ihre eigene Kennung. Die dieses Projekts bleibt angehängt, damit die Seite einen Menschen erreichen kann.
`BGF_MIN_INTERVAL_MS`	1500	1000 bis 60000
`BGF_TIMEOUT_MS`	20000	1000 bis 120000
`BGF_MAX_RETRIES`	3	0 bis 8
`BGF_CACHE_TTL_MS`	900000	0 bis 86400000, 0 schaltet den Speicher ab
`BGF_CACHE_MAX_ENTRIES`	200	1 bis 5000
`BGF_LOG_LEVEL`	`error`	`silent`, `error`, `info`, `debug`

Die Mindestfrequenz kann von außen nicht gesenkt werden. Die Seite ist kostenlos zu lesen und veröffentlicht keine Crawl-Verzögerung, was ein Grund zur Vorsicht ist, statt einer Lizenz, schnell zu sein.

Als Bibliothek

Die Leseschicht wird separat veröffentlicht, mit ihrer Frequenz, ihrem Speicher und ihrem Fehlervokabular und ohne angehängtes Protokoll:

import { GoodFoodClient } from "mcp-bbc-goodfood/client";

Fehler

Sechs Codes und nicht mehr. Ein Aufrufer verzweigt auf den Code, der die Meldung eröffnet.

Code	Was es bedeutet
`not_found`	Die Seite enthält nichts unter dieser Adresse
`invalid_input`	Die Argumente konnten keine Anfrage erzeugen
`rate_limited`	Die Seite hat diesen Client gebeten, langsamer zu machen. Es sagt nichts darüber, ob etwas übereinstimmte
`parse_failure`	Eine Antwort kam in einer Form an, die dieser Server nicht lesen kann
`network_error`	Die Anfrage konnte nicht abgeschlossen werden
`timeout`	Innerhalb der Frist kam keine Antwort an

Namensnennung

Rezepte, Titel und Zählungen gehören BBC Good Food. Jede Antwort trägt die Quelle, und eine Auflistung, die einem Leser gezeigt wird, sollte die Seite nennen und auf die Seite verlinken.

Mitwirken

Siehe CONTRIBUTING.md. Tests kommen zuerst, die Abdeckung hat eine Untergrenze von 100 %, und die Regel, der alles folgt, ist, dass der Server nie etwas sagt, das die Daten nicht enthalten.

Lizenziert unter MIT.

mcp-bbc-goodfood (Französisch)

Ein MCP-Server, der Rezepte von BBC Good Food liest. Nur lesend, ohne API-Schlüssel und ohne Konto.

Warum es das gibt

BBC Good Food akzeptiert jeden Wert auf einer Suchfacette und antwortet auf einen unbekannten Wert mit einer Gesamtzahl von null. Fragt man nach glutenfree statt gluten-free, antwortet die Seite, dass nichts übereinstimmt, mit der Sicherheit, mit der sie sagt, dass 48 Rezepte zur korrekten Schreibweise passen. Ein Modell, das eine Schreibweise errät, erhält eine selbstbewusste Abwesenheit statt einer Ablehnung.

Dieser Server veröffentlicht das Vokabular, damit die Frage gestellt werden kann.

Das Werkzeug

`list_filters`

Listet die Achsen auf, entlang derer eine Rezeptsuche eingegrenzt werden kann, mit den Werten, die jede annimmt, und der Anzahl der Rezepte, die sie tragen.

Argument	Typ	Bedeutung
`query`	Zeichenkette, optional	Misst die Zählungen innerhalb dieser Suche. Ohne ihn gelten sie für das gesamte Verzeichnis der Seite.

Die Seite zählt ihre Facetten über die Zeilen, die eine Suche zurückgibt, also beantworten die beiden verschiedene Fragen. Innerhalb von chicken meldet diet gluten-free 48. Über das gesamte Verzeichnis meldet es gluten-free 2810. Keines der beiden ist mit dem anderen vergleichbar, und die Antwort sagt, welchen Umfang sie gemessen hat.

Was die Antworten nicht behaupten

Die veröffentlichten Werte sind ein Auszug. Die Seite zeigt die zehn häufigsten Werte einer Achse und akzeptiert andere, die sie nie auflistet: cuisine=mexican grenzt eine Suche auf 306 Rezepte ein, ohne unter den zehn zu erscheinen. Die Antwort sagt, dass die Liste ein Auszug ist, statt sie die Menge der akzeptierten Werte zu nennen, denn ein Server, der sie so nennen würde, würde Werte ablehnen, die funktionieren.

Eine Zählung, für die die Seite nichts veröffentlicht hat, ist null, nie 0. Auf einer Skala, die bei null beginnt, wären die beiden nicht zu unterscheiden.

Die Seite beantwortet trotzdem einen Begriff, für den sie nichts hat. Die Suche nach foobar liefert sieben Rezepte, darunter einen Rhabarber-Cocktail und einen Flapjack-Riegel, die über Fragmente zusammengeführt wurden, ohne dass etwas die Antwort als Fehlschlag kennzeichnet. Jede Antwort liefert daher rows_seen und matched_rows: wie viele Zeilen die Seite geliefert hat und wie viele davon ein Wort der Suche tragen. Wenn die zweite null ist und die erste nicht, sagt eine Anmerkung, dass die Zählung beschreibt, was die Seite vorgeschlagen hat, statt was übereinstimmte.

Zwei Zählungen statt eines Urteils. Eine legitime Suche kann in keinem Titel vorkommen, und ein Leser, der 2 von 30 sieht, urteilt besser als eine Markierung, die für ihn urteilen würde.

Installation

npx mcp-bbc-goodfood

Claude Code

claude mcp add bbc-goodfood -- npx -y mcp-bbc-goodfood

Jeder MCP-Client

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

Container

docker build -t mcp-bbc-goodfood .
docker run -i --rm mcp-bbc-goodfood

Der Container muss www.bbcgoodfood.com erreichen können und sonst nichts. Er nimmt keine Anmeldedaten entgegen, da es keine zu nehmen gibt.

Einstellungen

Jede Einstellung ist eine Umgebungsvariable, und keine ist erforderlich. Ein Wert außerhalb der Grenzen wird mit einer Zeile auf stderr abgelehnt, und der Standardwert bleibt bestehen: Eine Einstellung, die nicht wirksam werden kann, sagt das, statt stillschweigend begrenzt zu werden.

Variable	Standard	Grenzen
`BGF_USER_AGENT`	—	Ihre Kennung. Die dieses Projekts bleibt angehängt, damit die Seite eine Person erreichen kann.
`BGF_MIN_INTERVAL_MS`	1500	1000 bis 60000
`BGF_TIMEOUT_MS`	20000	1000 bis 120000
`BGF_MAX_RETRIES`	3	0 bis 8
`BGF_CACHE_TTL_MS`	900000	0 bis 86400000, 0 schaltet den Speicher aus
`BGF_CACHE_MAX_ENTRIES`	200	1 bis 5000
`BGF_LOG_LEVEL`	`error`	`silent`, `error`, `info`, `debug`

Als Bibliothek

Die Leseschicht wird separat veröffentlicht, mit ihrer Frequenz, ihrem Speicher und ihrer Fehlertaxonomie, ohne angehängtes Protokoll:

import { GoodFoodClient } from "mcp-bbc-goodfood/client";

Fehler

Sechs Codes und nicht einer mehr. Ein Aufrufer verzweigt auf den Code, der die Meldung eröffnet.

Code	Bedeutung
`not_found`	Die Website hat an dieser Adresse nichts
`invalid_input`	Die Argumente konnten keine Anfrage erzeugen
`rate_limited`	Die Website hat gebeten, langsamer zu machen. Das sagt nichts darüber aus, was übereinstimmt
`parse_failure`	Eine Antwort ist in einer Form eingetroffen, die dieser Server nicht lesen kann
`network_error`	Die Anfrage konnte nicht abgeschlossen werden
`timeout`	Innerhalb der Frist ist keine Antwort eingetroffen

Namensnennung

Die Rezepte, Titel und Konten gehören BBC Good Food. Jede Antwort führt die Quelle an, und eine Auflistung, die einem Leser gezeigt wird, muss die Website nennen und auf die Seite verlinken.

Mitwirken

Siehe CONTRIBUTING.md. Tests zuerst, eine Mindestabdeckung von 100 %, und die Regel, die alles beherrscht: Der Server sagt nie etwas, das die Daten nicht hergeben.

Lizenziert unter MIT.

Available Tools

4 tools

get_recipeRead a recipeA

Read-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.

ParametersJSON Schema

Name	Required	Description
`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

ParametersJSON 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

A4.3/5.0

Behavior4/5

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.

Conciseness5/5

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.

Completeness5/5

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.

Parameters3/5

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.

Purpose5/5

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.

Usage Guidelines4/5

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 narrowedA

Read-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.

ParametersJSON Schema

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

ParametersJSON 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

A4.5/5.0

Behavior5/5

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.

Conciseness5/5

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.

Completeness5/5

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.

Parameters3/5

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.

Purpose5/5

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.

Usage Guidelines4/5

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 ingredientsA

Read-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.

ParametersJSON Schema

Name	Required	Description
`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

ParametersJSON 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

A4.6/5.0

Behavior5/5

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.

Conciseness4/5

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.

Completeness5/5

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.

Parameters4/5

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.

Purpose5/5

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.

Usage Guidelines4/5

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 recipesA

Read-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.

ParametersJSON Schema

Name	Required	Description
`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

ParametersJSON 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

A4.5/5.0

Behavior5/5

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.

Conciseness5/5

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.

Completeness5/5

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.

Parameters3/5

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.

Purpose5/5

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.

Usage Guidelines4/5

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 updatesv1.1.0Sep 10, 2026

Changedget_recipe23 fields changed

removedOutput schema / properties / author / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / author / type
```
Added value: +[
+  "string",
+  "null"
+]
```

removedOutput schema / properties / description / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / description / type
```
Added value: +[
+  "string",
+  "null"
+]
```

removedOutput schema / properties / difficulty / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / difficulty / type
```
Added value: +[
+  "string",
+  "null"
+]
```

removedOutput schema / properties / ingredients / items / properties / heading / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / ingredients / items / properties / heading / type
```
Added value: +[
+  "string",
+  "null"
+]
```

changedOutput schema / properties / ingredients / items / properties / ingredients / items / anyOf

Previous 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"
+  }
+]

removedOutput schema / properties / nutrition / items / properties / value / anyOf

Removed value: -[
-  {
-    "type": "number"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / nutrition / items / properties / value / type
```
Added value: +[
+  "number",
+  "null"
+]
```

removedOutput schema / properties / nutrition_per / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / nutrition_per / type
```
Added value: +[
+  "string",
+  "null"
+]
```

removedOutput schema / properties / rating / anyOf

Removed value: -[
-  {
-    "type": "number"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / rating / type
```
Added value: +[
+  "number",
+  "null"
+]
```

removedOutput schema / properties / yield / properties / factor / anyOf

Removed value: -[
-  {
-    "type": "number"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / yield / properties / factor / type
```
Added value: +[
+  "number",
+  "null"
+]
```

removedOutput schema / properties / yield / properties / original_text / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / yield / properties / original_text / type
```
Added value: +[
+  "string",
+  "null"
+]
```

removedOutput schema / properties / yield / properties / unit / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / yield / properties / unit / type
```
Added value: +[
+  "string",
+  "null"
+]
```

removedOutput schema / properties / yield_text / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / yield_text / type
```
Added value: +[
+  "string",
+  "null"
+]
```

Changedlist_filters4 fields changed
- removedOutput schema / properties / filters / items / properties / argument / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / filters / items / properties / argument / type
```
Added value: +[
+  "string",
+  "null"
+]
```
- removedOutput schema / properties / query / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / query / type
```
Added value: +[
+  "string",
+  "null"
+]
```
Changedscale_ingredients6 fields changed
- removedOutput schema / properties / ingredients / items / properties / amount / anyOf
```
Removed value: -[
-  {
-    "type": "number"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / ingredients / items / properties / amount / type
```
Added value: +[
+  "number",
+  "null"
+]
```
- removedOutput schema / properties / ingredients / items / properties / amount_max / anyOf
```
Removed value: -[
-  {
-    "type": "number"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / ingredients / items / properties / amount_max / type
```
Added value: +[
+  "number",
+  "null"
+]
```
- removedOutput schema / properties / ingredients / items / properties / unit / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / ingredients / items / properties / unit / type
```
Added value: +[
+  "string",
+  "null"
+]
```
Changedsearch_recipes8 fields changed
- removedOutput schema / properties / results / items / properties / author / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / results / items / properties / author / type
```
Added value: +[
+  "string",
+  "null"
+]
```
- removedOutput schema / properties / results / items / properties / difficulty / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / results / items / properties / difficulty / type
```
Added value: +[
+  "string",
+  "null"
+]
```
- removedOutput schema / properties / results / items / properties / image_url / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / results / items / properties / image_url / type
```
Added value: +[
+  "string",
+  "null"
+]
```
- removedOutput schema / properties / results / items / properties / rating / anyOf
```
Removed value: -[
-  {
-    "type": "number"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / results / items / properties / rating / type
```
Added value: +[
+  "number",
+  "null"
+]
```

4 tool updatesAug 29, 2026

Addedget_recipe

Changedlist_filters4 fields changed

addedOutput schema / properties / filters / items / properties / argument

Added 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."
+}

changedOutput schema / properties / filters / items / properties / name / description

Previous value: -"The argument name a search takes for this axis."New value: +"The site's own name for the axis."

changedOutput schema / properties / filters / items / properties / options / items / properties / value / description

Previous 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."

changedOutput schema / properties / filters / items / required

Previous value: -[
-  "name",
-  "label",
-  "options",
-  "option_count"
-]New value: +[
+  "name",
+  "label",
+  "argument",
+  "options",
+  "option_count"
+]

Addedscale_ingredients

Changedsearch_recipes4 fields changed

removedOutput schema / properties / restrictions_dropped

Removed value: -{
-  "description": "Restrictions the site could not answer, dropped so the search could run.",
-  "items": {
-    "type": "string"
-  },
-  "type": "array"
-}

addedOutput schema / properties / restrictions_lifted

Added value: +{
+  "description": "Restrictions let go of so the search could run again after the restricted one returned nothing.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

changedOutput schema / properties / results / items / properties / id / description

Previous 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."

changedOutput schema / required

Previous 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 updatesv0.1.0Aug 27, 2026
- First observedlist_filters
- First observedsearch_recipes

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.6/5.0

Scored 2026-09-10 23:30 across 4 tools

Disambiguation5/5

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.

Naming Consistency5/5

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.

Tool Count5/5

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.

Completeness5/5

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

ActivityActive

ResponsivenessUnresponsive

Resources

Need Help?

Related Servers

Related MCP Connectors

Tiny PlatesOAuth
io.github.Artmann
Search structured recipes, scale servings, match pantry ingredients, and build shopping lists.
1
Recipe Signal A
io.github.absharma9796
Search and compare attributed recipe records through a public read-only remote MCP endpoint.
Search Open Data
41
Recipes A
io.github.pipeworx-io
Recipes MCP — wraps TheMealDB API (free tier, no auth)
Search Open Data
2
PrepSheet
com.getprepsheet
Read-only kitchen costing, recipe scaling, UK GP, starter menus, and prep lists for chefs.
61

Related MCP Servers

mcp-spoonacular
Search Health & Wellness
pipeworx-io
A
license
Not graded
quality
B
maintenance
Provides access to the Spoonacular food API for recipes, nutrition, ingredients, and meal plans.
Updated 17 days ago (2026-09-26 21:42 UTC)
53 npm
MIT
mcp-cookbook
Search Entertainment & Media
springdo
F
license
Not graded
quality
D
maintenance
Enables browsing recipes, searching by category, and viewing detailed recipe information from the Gousto cookbook API via natural language.
Updated 6 months ago (2026-04-09 10:27 UTC)
-
mcp-openfoodfacts
Search Open Data
pipeworx-io
A
license
Not graded
quality
B
maintenance
Enables querying Open Food Facts product database by barcode, full-text search, category, brand, or country.
Updated 17 days ago (2026-09-26 20:13 UTC)
30 npm
MIT
MealCP MCPofficial
E-commerce & Retail Search
MealCP
A
license
A
quality
A
maintenance
Enables searching grocery product catalogs with faceted filters and retrieving price history statistics via the MealCP grocery price API.
Updated a month ago (2026-09-08 18:15 UTC)
2
MIT

mcp-bbc-goodfood

Warum es das gibt

Das Werkzeug

list_filters

Was die Antworten nicht überbewerten

Installation

Claude Code

Jeder MCP-Client

Container

Einstellungen

Als Bibliothek

Fehler

Namensnennung

Mitwirken

mcp-bbc-goodfood (Französisch)

Warum es das gibt

Das Werkzeug

list_filters

Was die Antworten nicht behaupten

Installation

Claude Code

Jeder MCP-Client

Container

Einstellungen

Als Bibliothek

Fehler

Namensnennung

Mitwirken

Available Tools

Output Schema

Output Schema

Output Schema

Output Schema

Tool Schema Changelog

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

MealCP MCPofficial

`list_filters`

`list_filters`