Nutritionix MCP. Turns meal descriptions into precise macro data.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Nutritionix provides natural language food analysis, letting your AI client pull precise macro and calorie breakdowns from descriptions like "3 slices of pizza and a coke." It’s an NLP engine that handles complex meal logging instantly.
Use it to analyze total caloric intake, protein counts, fat levels, and more for any food combination or specific branded item.
What your AI agents can do
Analyze food nutrition
Takes a text description of food and returns the precise nutritional breakdown (calories, macros) for every item listed.
Search nutritionix foods
Looks up common or brand-specific foods in the database to retrieve calorie data and key metrics.
Input raw text describing multiple foods (e.g., 'oatmeal, banana, peanut butter') and receive a structured breakdown of total macros and calories.
Search the database by food name or brand to retrieve calorie count and key metrics for individual items.
The tool provides separate, detailed metrics (protein, fat, carbs) for every ingredient listed in the input text.
It aggregates all nutritional data to provide a single, actionable total calorie count for the entire meal description.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Nutritionix MCP Server: 2 Tools for Food Analysis
Analyze food nutrition using natural language through two specialized tools designed for dietary data retrieval.
019d75e0analyze food nutrition
Takes a text description of food and returns the precise nutritional breakdown (calories, macros) for every item listed.
019d75e0search nutritionix foods
Looks up common or brand-specific foods in the database to retrieve calorie data and key metrics.
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 Nutritionix, 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
Look, stop trying to guess what you ate. Ya don't need to rely on memory or vague estimations for nutritional content; this server gives your AI client access straight into advanced food analysis. It processes raw text descriptions like 'three slices of pepperoni pizza and a Coke' and spits out precise macro and calorie breakdowns for every single thing mentioned.
When you use the analyze_food_nutrition tool, you feed it a natural language description of an entire meal, and it doesn't just give ya one number. It first calculates the detailed macro breakdown per item, providing separate metrics—protein, fat, and carbs—for every ingredient listed in that input text. After doing that deep dive on each part, the system aggregates all the data to determine a single, actionable total caloric intake for the whole meal description.
If you're just tracking one specific item or need to check out a particular brand, ya use search_nutritionix_foods. You search the database by food name or brand directly, and it pulls up the calorie count and key metrics for that individual product. This means you don't have to write a whole meal description if all you wanna know is about those specific protein bars.
This isn't just surface-level math; this engine handles complex logging instantly. When you input raw text describing multiple foods, like 'oatmeal, banana, peanut butter,' the system breaks down the exact nutritional content for every component listed in that meal description. You get metrics covering calories, protein, fat, carbs, fiber, sugar, sodium, and cholesterol—all structured data points, no fluff.
It's built to tell you what you actually got on your plate.
How Nutritionix MCP Works
- 1 Your agent receives a user query describing food (e.g., '2 eggs and toast').
- 2 The AI client calls
analyze_food_nutrition, passing the raw text to the server. - 3 The server returns structured data, listing every ingredient, its macro counts, and the final total breakdown.
The bottom line is: you feed it a list of foods in plain English, and you get back an organized spreadsheet full of nutritional facts.
Who Is Nutritionix MCP For?
Dietitians and health coaches who write client meal logs every day. Fitness app developers building tracking features. Data analysts working on wellness platforms that need high-accuracy food data without manual database upkeep.
Checks client recipe inputs against nutritional databases to ensure dietary goals are met or identify potential nutrient deficiencies.
Analyzes a user's daily food diary—which is often unstructured text—to provide immediate, quantifiable feedback on their macro intake.
Integrates reliable nutritional data into an app's logging feature, allowing users to enter meals via natural conversation instead of clicking through menus.
What Changes When You Connect
- Get a full breakdown of protein, fat, carbs, and fiber for every item. The
analyze_food_nutritiontool doesn't just give you calories; it separates out the actionable metrics needed for goal tracking. - Avoid manual lookups. You feed the agent unstructured text—like '3 slices of pizza and a coke'—and the
analyze_food_nutritiontool handles all the parsing, returning organized data instantly. - Checks brand consistency. Need to know the macros for a specific cereal box? Use
search_nutritionix_foodsto query branded items directly against the database. - Handles complexity. The server processes multi-component meals—like 'oatmeal with banana and peanut butter'—and provides an accurate total calculation, saving time over piecing together data from multiple sources.
- Saves development effort. Instead of building three separate API endpoints (search, macro, calorie), you use one robust NLP engine that handles the interpretation layer for you.
Real-World Use Cases
Logging a complex dinner meal
A user texts their agent: 'Last night I had steak and roasted asparagus.' The agent runs analyze_food_nutrition. It immediately returns the total calories, protein, and fat for both items, letting the user know if they were over budget without needing to search two separate menus.
Verifying a specific snack's macro count
A coach needs data on a new energy bar. They run search_nutritionix_foods with the brand name. This quickly returns the calorie and carb counts, allowing the coach to advise their client immediately.
Building an intake calculator
The system combines tools: first, it runs analyze_food_nutrition on a recipe list, then uses search_nutritionix_foods for any required supplemental ingredients (like oil), providing one single, complete nutritional summary.
Comparing meal options
The agent compares two different lunch options—one from the office cafeteria and one at home. By running analyze_food_nutrition on both text descriptions, it gives a side-by-side macro comparison to help the user choose better.
The Tradeoffs
Using general search for meal analysis
Asking your agent to 'find out what's in this pizza and coke.' A basic search tool might only return a list of ingredients, forcing you to manually calculate macros.
→
You must use analyze_food_nutrition. This specific tool takes the entire phrase ('pizza and coke') and returns the structured macro data for all components.
Querying single items vaguely
Just asking 'banana nutrition.' You might get generic info, but nothing tied to a specific brand or meal context.
→
For basic lookups, use search_nutritionix_foods. If the item is part of a larger list, include it in your text input and run analyze_food_nutrition for maximum detail.
Ignoring required units
Saying 'apple' without specifying quantity or type. The server can't calculate anything.
→ Be specific: always state the amount and unit (e.g., '1 medium apple,' or '200 grams of salmon'). This structured input is mandatory for accurate results from both tools.
When It Fits, When It Doesn't
Use this MCP Server if your goal involves quantifying nutritional intake based on natural language text, especially when dealing with complex recipes or meals composed of multiple items. You need the precision that only an NLP engine like Nutritionix can provide.
Don't use it if you are simply validating a known database entry (e.g., checking one item against USDA data—a basic search API might suffice). Also, don't expect it to handle nutritional information for non-food items (like medication or supplements) unless the tool supports those categories.
When in doubt: If you have a sentence that describes what someone ate, run analyze_food_nutrition. If you just need a quick check on one specific branded product name, use search_nutritionix_foods.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Nutritionix. 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 2 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Tracking meals shouldn't feel like doing homework.
Right now, logging food is painful. You find the recipe online, then you open a spreadsheet to track macros. You have to cross-reference every single ingredient—the toast, the butter, the OJ—and manually input those values. It's clicking through five different tabs and copying data into three separate columns.
With Nutritionix, that whole process goes away. Your agent takes the meal description in plain English, like 'breakfast of eggs and toast,' and it spits out a perfectly formatted breakdown: total calories, protein count, fat grams—all calculated automatically. You just get the answer.
Nutritionix MCP Server: Get accurate data instantly.
You don't have to juggle multiple databases or build complex parsing logic. The system handles recognizing that 'a Coke' is different from 'diet coke' and adjusts the macros accordingly, giving you actionable numbers immediately.
The result isn't just data; it’s clarity. You get a precise nutritional summary for any meal description, making your tracking process fast and reliable. It changes how accurate dietary logging can be.
Common Questions About Nutritionix MCP
How does `analyze_food_nutrition` work with restaurant chains? +
It accesses data from a database that includes extensive menu item information from national and regional restaurant chains. Just mention the name of the meal or dish, and it pulls the metrics.
Can I use `search_nutritionix_foods` to check for brands? +
Yes. This tool searches both generic foods and brand-specific items. You input a brand name, and it returns available calorie data for that product.
Does the MCP Server require me to write code to use `analyze_food_nutrition`? +
No. Your AI client handles the plumbing. You just need to tell your agent what you ate in plain language, and it calls the tool for you.
Is there a difference between the two tools? +
Yes. Use search_nutritionix_foods when you only want to look up one specific item or brand. Use analyze_food_nutrition when you have multiple items in one meal and need a total breakdown.
What credentials does the Nutritionix MCP Server require for `analyze_food_nutrition`? +
You need an app_id and app_key to connect. These keys grant your agent secure access to the service. You get these credentials directly from your Nutritionix account dashboard.
Are there any rate limits when using `analyze_food_nutrition`? +
Yes, standard API rate limiting applies. If you hit a limit, your agent will receive an HTTP 429 error. Check the developer documentation for specific thresholds and proper retry logic.
Does the result from `analyze_food_nutrition` always include specific macro details? +
Yes, it returns a full nutritional breakdown per item. You get calories plus protein, fat, carbs, fiber, sugar, sodium, and cholesterol for everything you list in your prompt.
What should I do if `analyze_food_nutrition` fails to parse my meal description? +
The tool returns specific error codes explaining the failure. If parsing fails, try simplifying or rephrasing your input text. Being more direct usually fixes most recognition issues.
How accurate is the NLP food analysis? +
Nutritionix's NLP engine is used by major fitness and health apps globally. It can parse complex meal descriptions including quantities, cooking methods, and brand names with high accuracy, backed by a verified database of 1M+ food items.
Can it recognize branded foods or restaurant items? +
Yes, Nutritionix excels at this. If you type '1 Big Mac and a medium fries from McDonald's', it will correctly map these to specific branded items in its database.
Does it track micronutrients? +
Yes, in addition to macros (proteins, fats, carbs), it returns data on dietary fiber, sugars, sodium, cholesterol, and potassium for an incredibly comprehensive nutritional profile.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
6sense
Account-based marketing intelligence — identify anonymous visitors, enrich company data, and track intent via AI.
HowLongToBeat
Universal game completion data — get gameplay hours for any video game via AI.
Parknav
AI-powered predictive parking availability and street occupancy data via Parknav API.
You might also like
ANOVA Calculator Engine
Run exact One-Way ANOVA tests to compare means across multiple groups local. Get CPU-guaranteed F-scores and p-values, not LLM guesses.
Metatext
No-code NLP and AI model management via Metatext — run inference and manage datasets.
SmartChatAI
Manage AI bots, knowledge bases, and messaging on SmartChatAI with AI agents.