This server provides semantic recipe search over ~50,000 Food.com recipes, plus a basic connectivity test.
Search recipes using natural language queries in any language (auto-translated to English), supporting search by cuisine, cooking style, ingredient, occasion, or mood (e.g. "quick Italian pasta", "healthy high-protein chicken bowl")
Filter by dietary requirements: vegetarian, vegan, gluten-free, dairy-free, low-carb, keto, or paleo
Filter by difficulty level: easy, medium, or hard
Filter by maximum cooking time in minutes
Control the number of results (default 5, up to 20)
Results include nutritional info, difficulty ratings, and user ratings
Ping / connectivity test to confirm the server is running
Provides semantic search capabilities for food recipes through LangChain integration, enabling AI agents to query recipes by natural language with filtering by diet, difficulty, time, and servings.
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.
Live endpoint: https://recipes.aidatanorge.no/mcp
Transport: streamable-http
Demo: https://recipes.aidatanorge.no/
Add to your MCP client config:
{
"mcpServers": {
"food-recipe": {
"type": "streamable-http",
"url": "https://recipes.aidatanorge.no/mcp"
}
}
}Or with Claude Code:
claude mcp add --transport http food-recipe https://recipes.aidatanorge.no/mcpRelated MCP server: Food MCP Server
Try the live demo in your browser:
https://recipes.aidatanorge.no/
No installation or configuration needed.
search_recipesSemantic search over 50,000+ recipes from Food.com with hybrid retrieval and reranking.
search_recipes(
query="quick Italian pasta for weeknight dinner",
diet="vegetarian", # vegetarian | vegan | gluten-free | dairy-free | low-carb | keto | paleo
max_minutes=30, # maximum total cooking time in minutes
difficulty="easy", # easy | medium | hard
limit=5 # default 5, max 20
)
# Returns: rerank_score, rrf_score, title, description, total_time, difficulty,
# diet, main_ingredient, servings, ingredients, instructions, nutrition,
# rating, rating_count, source, recipe_idQuery examples:
"Swedish meatballs with gravy"
"healthy high-protein chicken bowl"
"easy chocolate cake for beginners"
"traditional Norwegian kjøttkaker"
"hurtig pasta med kylling"
Search pipeline: Dense embedding (intfloat/e5-large-v2, 1024d) + sparse BM25, fused via Reciprocal Rank Fusion (RRF), reranked by mmarco-mMiniLMv2-L12-H384-v1.
pingping(name="world")
# Returns: "Hello world! Recipe MCP server is running."Source: Food.com (~50,000 recipes)
Coverage: Wide range of cuisines, meal types, and cooking styles
Nutritional data: calories, fat, protein, carbohydrates, sodium, fiber, sugar per serving
Ratings: user rating + rating count per recipe
Languages: English and Norwegian supported natively in queries
Food.com recipes → Python ingest → Qdrant (recipe_data_v2 collection)
↓
Hybrid search (dense e5-large-v2 + sparse BM25)
↓
RRF fusion + cross-encoder reranking
↓
FastMCP 3.2 → MCP clients / AI agentsEmbeddings: intfloat/e5-large-v2 (1024d dense) + Qdrant/bm25 (sparse)
Reranker: cross-encoder/mmarco-mMiniLMv2-L12-H384-v1
Vector DB: Qdrant (self-hosted)
Server: FastMCP 3.2 over HTTP
Infrastructure: Ubuntu Server 24 LTS, Cloudflare Tunnel
MIT
Simple connectivity test. Returns a greeting to confirm the server is running.
Inputs: name. Returns: result
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. Queries in any language are supported and will be automatically translated to English before search. 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'
Inputs: query (required), diet, max_minutes, difficulty, +2 more. Returns: result
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 2 tools
The two tools have completely distinct purposes: ping is a connectivity test with no domain functionality, while search_recipes is the core recipe search operation. There is no overlap or ambiguity between them.
Both tools use snake_case naming, which is consistent. However, ping uses a generic network term while search_recipes follows a verb_noun pattern, creating a minor deviation in naming style.
With only 2 tools, this server feels severely under-equipped for a recipe domain. A recipe server should typically include tools for retrieving recipe details, filtering by criteria, saving favorites, or managing collections, not just search and ping.
The server lacks basic CRUD operations for recipes. While search_recipes is well-described, there are no tools to get full recipe details, create/modify recipes, or manage user interactions. This creates significant gaps for agent workflows.
Cloud or self-hosted knowledge for AI agents: hybrid search, reranking, GraphRAG, scoped MCP tools.
Recipe search, ingredient matching, nutrition filters and a private cookbook for any AI agent.
Web search API and MCP server for developers building AI agents.
