For Agents
Search and read Swedish recipes with ingredients, amounts, steps, EU 14 allergens, and timings, and look up ingredient data such as allergens and density for unit conversion.
Use for: Find a Swedish recipe that uses lingonberries, Get the full ingredient list and steps for a kanelbullar recipe, Check which allergens a recipe contains, Search for vegetarian dinner recipes
Not supported: Does not create or edit recipes, plan meals, order groceries, or give medical allergy advice. Use for reading Swedish recipe and ingredient data only.
The ReceptAPI API serves Swedish recipes as structured data, with ingredients, the EU 14 allergens, cooking steps, and serving information. Recipes can be listed by free text, category, tag, or ingredient, or fetched in full by slug with amounts, units, nutrition, difficulty, and total and active minutes. An ingredient endpoint returns each ingredient's Swedish name, allergens, default unit, density in grams per decilitre, and its Livsmedelsverket id. Free-tier use requires the attribution line returned in every response's meta block.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the ReceptAPI, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Freceptapi.se%2Freceptapi" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Freceptapi.se%2Freceptapi" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with ReceptAPI API.
Search Swedish recipes by free text across titles, descriptions, tags, and ingredients
Filter the recipe list by category, tag, or an ingredient slug such as a specific vegetable
Fetch a full recipe by slug with ingredient amounts, units, groups, steps, nutrition, and allergens
Look up an ingredient's allergens, default_unit, density_g_per_dl, and livsmedelsverket_id
Find ingredients by Swedish name or alias and see how many recipes use each one
Patterns agents use ReceptAPI API for, with concrete tasks.
★ Allergy-aware cooking assistant through Jentic
A meal-planning agent asked for a dinner without milk or gluten needs real recipes with declared allergens rather than guesses. Through Jentic the agent searches for 'find a Swedish recipe', loads the ReceptAPI recipe search and detail operations with their input schemas, and reads the allergens array on each candidate recipe, with the optional API key injected at call time. It can then present only recipes whose allergens exclude mjolk and gluten, along with the required attribution line.
Call GET /recipes with q 'middag' and limit 20, then GET /recipes/{slug} for each result and keep only recipes whose allergens include neither 'mjolk' nor 'gluten'
Ingredient-led recipe discovery
A food app suggests what to cook from what is already in the fridge. ReceptAPI filters the recipe list by an ingredient slug, and the ingredients endpoint resolves a Swedish name or alias to that slug and reports how many recipes use it. The app chains the two to show matching recipes with servings, total_minutes, and difficulty.
Call GET /ingredients with q 'potatis' to get the ingredient slug, then GET /recipes with ingredient set to that slug and limit 10
Grams-and-decilitres unit conversion
Swedish recipes measure dry goods in decilitres, while nutrition and shopping tools often need grams. ReceptAPI returns density_g_per_dl and default_unit for each ingredient, so a tool can convert a recipe's amounts between volume and weight with the vendor's own figures rather than a generic table.
Call GET /ingredients/{slug} for 'vetemjol' and multiply 3 dl by density_g_per_dl to return the weight in grams
5 endpoints — the receptapi api serves swedish recipes as structured data, with ingredients, the eu 14 allergens, cooking steps, and serving information.
METHOD
PATH
DESCRIPTION
/recipes
List recipes by text, category, tag, or ingredient
/recipes/{slug}
Get a full recipe
/search
Search recipes
/ingredients
List ingredients by name or alias
/ingredients/{slug}
Get an ingredient
/recipes
List recipes by text, category, tag, or ingredient
/recipes/{slug}
Get a full recipe
/search
Search recipes
/ingredients
List ingredients by name or alias
/ingredients/{slug}
Get an ingredient
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>What agents get from Jentic-routed access to this vendor.
Setup
Wiring ReceptAPI by hand means deciding whether to send a key in the x-api-key header, tracking the daily call caps, and carrying the attribution line from meta into what you display. Through Jentic you install once, import ReceptAPI from the API Directory, store the key once, and your agent calls it.
Permission scoping
ReceptAPI is read-only and puts the recipe or ingredient slug in the URL path (/recipes/{slug}), so a rule can bound your agent to the read operations you pick, down to one recipe if you want. You choose which of the five operations it may call.
Credential isolation
If you use a ReceptAPI key, it is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'find a Swedish recipe' or 'get an ingredient's allergens', and Jentic returns the matching ReceptAPI operation with its input schema, including the q, category, tag, and ingredient filters.
Alternatives and complements available in the Jentic catalogue.
Specific to using ReceptAPI API through Jentic.
What authentication does ReceptAPI use?
Per its OpenAPI spec, ReceptAPI takes an optional API key in the x-api-key header, and its security block also allows anonymous calls. The spec states anonymous calls get 50 a day per IP and a free key raises that to 100 a day. Through Jentic the key, if you use one, is stored by your own instance and attached at call time.
What are the rate limits for ReceptAPI?
The spec's own description states the limits: anonymous calls are capped at 50 a day per IP, and a free API key allows 100 a day. Check https://receptapi.se/ for any paid tiers above that.
Do I need to credit ReceptAPI when I use its data?
Yes, on the free tier. The spec states that all free-tier use requires attribution, and every response carries the required credit text, naming ReceptAPI and receptapi.se, in meta.attribution. Show that line wherever your agent displays the recipe.
Is there a ReceptAPI MCP server?
You don't need an MCP server to give your agent ReceptAPI. Jentic connects it directly from the API Directory: import it, store your key once if you have one, and your agent calls the recipe and ingredient operations on demand without loading extra tool definitions into its context.
How do I get a recipe's allergens through Jentic?
Search Jentic for 'get a Swedish recipe with allergens', load the GET /recipes/{slug} operation, and run it with the recipe slug. The response carries an allergens array using codes such as gluten, mjolk, and agg, along with the ingredient list. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Can I limit what my agent is allowed to do with ReceptAPI?
Yes. For example, write a rule that allows only GET /recipes and GET /recipes/{slug}, so the agent can search and read recipes but not page through the ingredient database, and every call it makes is logged.
GET STARTED