Spoonacular MCP. Build meal plans from available ingredients.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Spoonacular connects your AI client to a full recipe intelligence platform. You can find recipes based on ingredients you have, plan meals with dietary constraints (vegan, keto, paleo), or get complete nutritional breakdowns for any dish.
It handles everything from pantry raids to professional meal planning.
What your AI agents can do
Find recipes by ingredients
Takes a comma-separated list of ingredients and finds recipes that use what you have in your kitchen.
Get random recipes
Provides random recipe suggestions when the user needs quick meal inspiration or is bored with cooking.
Get recipe details
Retrieves complete information for one recipe, including instructions, full ingredient lists, and nutritional facts.
The agent processes a list of available food items and returns viable recipe options that use most or all of those inputs.
You can narrow down searches by setting parameters like 'gluten-free,' 'vegetarian,' 'Italian,' or a maximum calorie count.
The tool calculates and returns detailed metrics, including calories, protein, fat, and carbohydrates, for a given dish.
If the user needs inspiration, this capability pulls random recipes to break through decision paralysis.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Spoonacular MCP Server: 4 Tools for Recipes
These tools let you search recipes using filters, find dishes from specific ingredients, check nutrition facts, or just get random ideas.
019d760bfind recipes by ingredients
Takes a comma-separated list of ingredients and finds recipes that use what you have in your kitchen.
019d760bget random recipes
Provides random recipe suggestions when the user needs quick meal inspiration or is bored with cooking.
019d760bget recipe details
Retrieves complete information for one recipe, including instructions, full ingredient lists, and nutritional facts.
019d760bsearch recipes
Finds recipes using optional filters like cuisine type, diet (vegan, paleo), or maximum calorie count.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Spoonacular, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
Spoonacular hooks your agent up to a massive recipe intelligence platform. You're not just searching for recipes; you're planning whole meals based on what's actually hanging out in your kitchen or sticking to some strict diet plan. It handles everything, from that random pantry haul to professional-grade meal prep.
If you need help figuring out dinner tonight, this server gives you four tools that cover every angle: finding recipes using specific ingredients, filtering by diet rules and cuisine type, getting full nutritional data on any dish, or just generating some spontaneous ideas when you're totally lost.
To find recipes based on what you have right now, use find_recipes_by_ingredients. You feed it a comma-separated list of ingredients, and the agent returns viable recipe options that maximize the use of everything you listed. This is perfect for avoiding food waste because it focuses on utilizing your existing inventory.
If you know exactly what kind of meal you want, or if you're sticking to rules like keto, paleo, or gluten-free, start with search_recipes. You can narrow down searches by setting parameters such as a cuisine type—like Italian or Mexican—or limiting the recipe search to a maximum calorie count. This tool gives you control over the whole scope of your meal plan.
Need inspiration? When you're staring into a fridge and nothing sounds good, run get_random_recipes. It pulls random suggestions that can break through decision paralysis and get you started cooking right away.
Once you pick a recipe—whether it was found by ingredients or filtering—you use get_recipe_details to pull the full rundown. This tool gives you complete instructions, every single ingredient required, and detailed nutritional facts for the dish, including exact metrics for calories, protein, fat, and carbohydrates.
Your agent processes a list of available food items through find_recipes_by_ingredients, returning recipes that use most or all of those inputs. You can restrict your searches using search_recipes by setting filters like 'vegetarian,' 'Italian,' or capping the maximum number of calories allowed in the meal. If you're just bored and need a quick idea, running get_random_recipes provides unexpected suggestions immediately.
Finally, when you commit to a dish, get_recipe_details calculates and returns detailed metrics for that specific recipe, giving you full instructions, complete ingredient lists, and precise nutritional breakdowns.
How Spoonacular MCP Works
- 1 You tell your agent what you want: either a list of ingredients or a specific search constraint (e.g., 'keto' and 'Mexican').
- 2 Your agent calls the appropriate tool (
find_recipes_by_ingredientsorsearch_recipes), passing the data to Spoonacular. - 3 The server returns a curated list of recipes, which you can then pass to
get_recipe_detailsto get the full instructions and nutritional facts.
The bottom line is: it turns your raw inputs—whether they're ingredients or dietary restrictions—into actionable meal plans with exact cooking steps.
Who Is Spoonacular MCP For?
Anyone who has to figure out dinner when the pantry looks depressing. This is for people dealing with food waste, managing diets (like keto or paleo), or just tired of eating takeout. If you spend time scrolling through recipe apps feeling overwhelmed by choices, this server cuts right to what you can actually make.
Uses find_recipes_by_ingredients first thing in the morning to plan meals based on perishable groceries before they go bad.
Relies on search_recipes and get_recipe_details to quickly cross-reference client dietary restrictions (e.g., 'low sodium, high fiber') with specific recipes.
Integrates the server's tools into an application flow to provide structured recipe suggestions and nutritional data endpoints for a consumer-facing product.
What Changes When You Connect
- Stop wasting food. By using
find_recipes_by_ingredients, you tell your agent exactly what's in the pantry, and it returns recipes that use those items—no guessing needed. - Pinpoint dietary safety instantly. The
search_recipestool lets you filter by specific diets (e.g., gluten-free or whole30) so you never have to check labels again. - Get the full facts. After finding a dish, run
get_recipe_detailsto get the precise breakdown of calories, protein, and fat per serving. - Need an idea fast?
get_random_recipeshandles the initial decision paralysis by giving you quick, surprise suggestions without needing any input from you. - Filter down complex searches. Instead of general searching, use
search_recipesto narrow results first by cuisine (Thai) and then by constraint (under 400 calories).
Real-World Use Cases
Pantry Raid: Nothing is expiring
A user notices half a bag of rice, some garlic, and chicken breast are about to spoil. They ask their agent what they can make with these items. The agent uses find_recipes_by_ingredients and returns several options like 'Garlic Chicken Rice Bowl,' solving the immediate waste problem.
Dinner Planning for a Restricted Diet
A user needs dinner that is vegan and low-carb. They ask their agent to search recipes, specifying both filters. The agent calls search_recipes with 'vegan' and 'keto', narrowing the field instantly.
Deep Dive into Nutrition
After finding a potential recipe, the user needs to verify the sugar content for a client. They call get_recipe_details, which returns the full nutritional data, including specific carb and protein counts, so they can confirm its suitability.
Boredom Buster Meal Prep
It's 7 PM, and everyone is tired. The user asks for a random dinner idea. The agent calls get_random_recipes, providing immediate inspiration like 'Spicy Coconut Curry,' which they can then verify with get_recipe_details.
The Tradeoffs
Using general search for ingredients
Asking the agent, 'What should I make with chicken and rice?' and relying solely on the broad search results.
→
Don't use search_recipes. Instead, call find_recipes_by_ingredients and pass 'chicken, rice.' This forces the tool to prioritize recipes that maximize your available inventory.
Ignoring nutritional constraints
Getting a list of 20 great-looking recipes but having no idea if they are suitable for a client with allergies or diabetes.
→
Always run search_recipes first, making sure to apply filters like 'gluten-free' or setting maximum calories. This cuts the pool down before you even look at ingredients.
Calling `get_recipe_details` without a recipe ID
Telling the agent, 'Tell me about the instructions.' The tool requires a specific recipe to run.
→
You must first use one of the search tools (find_recipes_by_ingredients, etc.) to get a list. Then, pass the resulting ID or title into get_recipe_details.
When It Fits, When It Doesn't
Use this MCP Server if your core need is connecting physical groceries/dietary rules to actionable cooking instructions. You're dealing with food waste, specialized diets (keto, paleo), or complex meal planning.
Don't use it if you simply need general information—like 'what are the benefits of turmeric?' for that, a knowledge base API works better. Also, don't rely on get_recipe_details to do your search; always start by calling either find_recipes_by_ingredients or search_recipes first. These two tools determine the scope of possibilities; get_recipe_details just gives you the manual for one specific item.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Spoonacular. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 4 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Pantry raid panic shouldn't require a trip to Google and three different tabs.
Right now, if you open your fridge and realize you have random leftovers—some pasta, some ground beef, some spinach—you spend twenty minutes opening recipe websites. You type in 'pasta,' see 50 results, then filter by 'beef.' Then you check the ingredients to see if they actually use all the spinach. It's a mess of copy-pasting and guessing.
With this MCP Server, your agent handles the whole sequence. Instead of searching generally, you just tell it: 'I have pasta, ground beef, and spinach.' The server runs `find_recipes_by_ingredients`, instantly showing only viable dishes that use everything up. You get a plan in seconds.
The Spoonacular MCP Server gives you total control over nutritional planning.
Before, if you found a recipe you liked, you had to assume it was okay for your client's diet. You'd search elsewhere for calorie counts or carb breakdowns, creating friction between the discovery and the validation stages.
Now, after finding an idea using `search_recipes`—maybe a Thai curry—you can pass that recipe ID straight into `get_recipe_details`. You get the full nutritional breakdown (calories, protein, etc.) right in your workflow. The entire process is self-contained.
Common Questions About Spoonacular MCP
How do I find recipes using Spoonacular's find_recipes_by_ingredients tool? +
You list the ingredients you have available, separated by commas. For example: 'chicken, rice, garlic'. The server then returns recipe ideas that maximize your inventory.
Can I search for gluten-free recipes using search_recipes? +
Yes. When calling search_recipes, you pass the dietary filter 'gluten-free' along with any cuisine or calorie limits to narrow down results immediately.
What information does get_recipe_details provide? +
It provides everything needed: step-by-step instructions, a full list of ingredients, and the complete nutritional breakdown for one specific recipe item.
How do I generate meal ideas without inputting anything? +
Just use get_random_recipes. This tool bypasses searching entirely and provides quick suggestions when you're just looking for inspiration.
What should I know about usage limits when using search_recipes? +
The free tier allows up to 150 requests per day. If you exceed this limit, the API will return a rate limit error. For consistent use or higher volumes, you'll need to upgrade your subscription.
How do I use find_recipes_by_ingredients for specific cuisine types? +
You can combine ingredient input with other filters when calling the tool. While 'find_recipes_by_ingredients' focuses on what you have, you often need to pair it with optional filters like 'cuisine' in a subsequent call.
When I use get_recipe_details, is all the nutritional data available? +
Yes. The tool provides a complete breakdown including calories, protein, fat (and saturated fat), carbohydrates, fiber, and sodium counts for accurate meal planning.
Does search_recipes support filtering by calorie maximums or cooking time? +
Absolutely. You can pass optional filters to 'search_recipes' that let you define a max calorie count or specify the maximum allowed preparation and cook time for your recipes.
What dietary filters are available? +
Spoonacular supports: vegetarian, vegan, gluten-free, ketogenic, paleo, whole30, lacto-vegetarian, ovo-vegetarian, pescetarian, and primal diets. You can also filter by intolerances like dairy, egg, gluten, peanut, sesame, and soy.
Can I get full nutritional analysis for the recipes? +
Yes, every recipe includes a comprehensive nutritional breakdown including calories, macronutrients, and micronutrients.
Is there a limit to the daily requests on the free tier? +
Yes, the free tier allows up to 150 points (requests) per day.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Tettra
Search, read, and create internal wiki pages on your Tettra knowledge base directly from your AI agent.
Dext
Equip your AI agent to manage receipts, track invoices, and monitor accounting data via the Dext API.
HubSpot CRM
Search, create, and manage HubSpot contacts, companies, notes, tasks, and associations through natural conversation.
You might also like
4YouSee
Digital signage management platform — monitor players, manage media, and audit content via AI.
RateUpdate
Manage hotel rates and availability across OTAs and booking channels with centralized distribution and pricing intelligence.
Outreach
Equip your AI agent with direct access to Outreach — manage prospects, track sequences, and analyze sales engagement without opening the Outreach platform.