food-recipe-mcp

search_recipes

Read-only

Search a database of recipes using hybrid semantic search (dense + sparse) with reranking.

The database contains ~50,000 recipes from Food.com covering a wide range of cuisines, meal types, and cooking styles. Recipes include nutritional information, difficulty ratings, and user ratings.

Use natural language in the query to describe what you are looking for — cuisine, style, main ingredient, occasion, or mood all work well. Norwegian and English are both supported natively. Examples: 'quick Italian pasta for weeknight dinner' 'Swedish meatballs with gravy' 'healthy high-protein chicken bowl' 'easy chocolate cake for beginners' 'something with salmon and lemon' 'Indian curry chicken' 'traditional Norwegian kjøttkaker' 'hurtig pasta med kylling' 'enkel sjokoladekake'

Args: query: What you are looking for — describe the dish, cuisine, main ingredient, cooking style or mood freely. Any language is supported. diet: Optional — filter by dietary requirement: 'vegetarian', 'vegan', 'gluten-free', 'dairy-free', 'low-carb', 'keto', 'paleo' max_minutes: Optional — maximum total time in minutes, e.g. 30 difficulty: Optional — 'easy', 'medium' or 'hard' servings: Optional — not used for filtering (servings vary), but include in query for scaling context, e.g. 'pasta dish for 6 people' limit: Number of results to return after reranking (default 5, max 20)

Returns: List of recipes ranked by relevance. Each result includes rerank_score, rrf_score (hybrid fusion), title, total_time, difficulty, diet labels, ingredients, instructions, nutrition, rating, and source URL context.

Input Schema

TableJSON Schema

Name	Required	Description
`diet`	No	Optional dietary filter: vegetarian, vegan, gluten-free, dairy-free, low-carb, keto, or paleo
`limit`	No	Number of results to return after reranking (1–20, default 5)
`query`	Yes	Natural language description of what you want, e.g. 'quick Italian pasta' or 'enkel sjokoladekake'
`servings`	No	Not used for filtering — include serving size context in query instead, e.g. 'pasta for 6 people'
`difficulty`	No	Optional difficulty filter: easy, medium, or hard
`max_minutes`	No	Optional maximum total cooking time in minutes, e.g. 30. Use 0 for no limit

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedApr 29, 2026

addedInput schema / properties / diet / description

Added value: +"Optional dietary filter: vegetarian, vegan, gluten-free, dairy-free, low-carb, keto, or paleo"

addedInput schema / properties / difficulty / description

Added value: +"Optional difficulty filter: easy, medium, or hard"

addedInput schema / properties / limit / description

Added value: +"Number of results to return after reranking (1–20, default 5)"

addedInput schema / properties / max_minutes / description

Added value: +"Optional maximum total cooking time in minutes, e.g. 30. Use 0 for no limit"

addedInput schema / properties / query / description

Added value: +"Natural language description of what you want, e.g. 'quick Italian pasta' or 'enkel sjokoladekake'"

addedInput schema / properties / servings / description

Added value: +"Not used for filtering — include serving size context in query instead, e.g. 'pasta for 6 people'"

Changed1 schema field changedApr 15, 2026
- addedOutput schema / description
```
Added value: +"Generic wrapper for non-object return types."
```
First observedApr 11, 2026

TDQS

A4.7/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnlyHint annotation, the description discloses substantial behavioral traits: hybrid search mechanics (dense+sparse), reranking, database scope (~50,000 recipes), result fields (rerank_score, rrf_score, etc.), and the limitation that servings is not used for filtering. This far exceeds the annotation's minimal safety signal.

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 well-structured with clear sections (database context, usage examples, args, returns). It front-loads the core purpose and every sentence, including the seven query examples, adds practical value. The length is justified by the need to explain hybrid search, filters, and result contents.

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 fully self-contained: it explains the database scope, query language support, all parameters, return fields, and limitations. Even with an output schema available, it details what each result contains (rerank_score, rrf_score, ingredients, nutrition, etc.), making it complete for an agent to select and invoke correctly.

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?

Schema coverage is 100%, but the description adds significant meaning beyond each parameter's schema description. For example, it clarifies that servings should be included in query context, states that query supports any language, and gives concrete example values for each parameter. This goes above the baseline for high schema coverage.

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 immediately states a specific verb+resource: 'Search a database of recipes using hybrid semantic search (dense + sparse) with reranking.' This clearly distinguishes the tool from the only sibling 'ping' and leaves no ambiguity about its function.

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 provides rich usage guidance, including natural language query examples, supported languages (Norwegian and English), and filter options. It also clarifies that 'servings' is not for filtering but should be included in the query. However, it does not explicitly state when not to use the tool or name alternatives beyond the sibling ping, so it falls short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All food-recipe-mcp tools Inspect

Try in Browser

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

Glama MCP Gateway

Add one secure layer between your agents and this server.