This MCP server provides semantic search across 50,000+ food recipes, intended for AI agents and LLMs. It uses a two-stage hybrid retrieval approach that combines dense and sparse BM25 results fused via RRF, then applies cross-encoder reranking. Queries can be sent in Norwegian and English.
🛠️ Key Features
Semantic search over 50,000+ food recipes
Hybrid retrieval: dense + sparse BM25
Fusion via RRF and cross-encoder reranking
Natural language queries in Norwegian and English
2 tools (toolCount: 2)
🚀 Use Cases
Querying large recipe collections using natural language
Agent workflows needing retrieval plus reranking for relevant recipes
⚡ Developer Benefits
Designed for AI agents and LLM integration
Live MCP endpoint: https://recipes.aidatanorge.no/mcp
Only supports semantic search described in the provided documentation (no additional tools or capabilities listed).
Topics
fastmcpfoodmcprecipessemantic-search
Captured live from the server via tools/list.
ping
Simple connectivity test. Returns a greeting to confirm the server is running.
Parameters1
name
string
optional
Arbitrary label included in the response, e.g. 'healthcheck'
Raw schema
{
"type": "object",
"properties": {
"name": {
"default": "world",
"description": "Arbitrary label included in the response, e.g. 'healthcheck'",
"type": "string"
}
},
"additionalProperties": false
}
search_recipes
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.
Parameters6
query
string
required
Natural language description of what you want, e.g. 'quick Italian pasta' or 'enkel sjokoladekake'
Semantic search over 50,000+ food recipes — built for AI agents and LLMs. Two-stage hybrid retrieval (dense + sparse BM25, fused via RRF) with cross-encoder reranking. Supports natural language queries in Norwegian and English.