Free · Open source · OAuth 2.0

Track your nutrition by talking to your AI.

Connect Claude or ChatGPT, then just say what you ate. Calories and macros, logged automatically.

Quick install Support

Nutrition MCP online

Log oatmeal with banana and peanut butter for breakfast

Done — added that to breakfast: oatmeal, banana, and peanut butter. That's about 420 kcal (14g protein, 62g carbs, 14g fat). Here's where you are today:

Calories 420 / 2,100

Protein 14 / 150 g

Carbs 62 / 220 g

Show my trends this week

You're averaging around 1,980 kcal a day this week — about 5% under your goal. Protein's up ~12g from last week, and you're on a 6-day logging streak. Nice work!

Message Nutrition…

How it works

Three steps. No app to learn.

1 · Connect once

Works with any AI client that supports remote MCP servers — Claude, ChatGPT, and more. No install, no API keys.

2 · Just say what you ate

Describe it in plain language — or send a photo of your meal, a screenshot from a delivery app, or a barcode (it looks the product up online). Macros logged automatically.

3 · Track & review

Ask for daily summaries, weekly trends, goal progress, or export it all to CSV — completely free.

Quick install

Connect in under a minute

Works with any MCP client that supports OAuth 2.0 with PKCE. On first connect you create an account with Google or an email and password; sign in the same way to keep your data.

Claude ChatGPT Other agents

Open Claude (web or desktop) and click Customize in the top-left corner.
Click Connectors.
Click +, then Add custom connector.
Give it a name, for example Nutrition.
Paste https://nutrition-mcp.com/mcp into the Remote MCP server URL field.
Click Add.
Click Connect — the login page opens; continue with Google or sign in with an email and password.
Done. It works right away and shows up in your iOS and Android apps automatically.

Works on every Claude plan. The free plan allows one connected MCP server at a time.

Open ChatGPT on the web → Settings → Apps.
Click Create app at the bottom of the popup. If you don't see it, turn on Developer mode in Advanced settings.
Give it a name, for example Nutrition.
For Connection, paste https://nutrition-mcp.com/mcp.
For Authentication, choose OAuth — leave everything else as it is.
Check "I understand and want to continue".
Click Create.
Click Sign in with Nutrition — the login page opens; continue with Google or sign in with an email and password.
Done. It works right away and shows up in your iOS and Android apps automatically.

{
  "mcpServers": {
    "nutrition": {
      "url": "https://nutrition-mcp.com/mcp"
    }
  }
}

Add the config above to your client (Cursor, VS Code, Claude Code, and more). Windsurf uses serverUrl instead of url. In Claude Code, run claude mcp add --transport http nutrition https://nutrition-mcp.com/mcp. Your client handles the OAuth login automatically.

Try saying

Just talk to it.

A few of the things you can do — just by talking.

Nutrition MCP online

Log a chicken burrito bowl for lunch

Got it — added a chicken burrito bowl to lunch, about 650 kcal (42g protein, 68g carbs, 22g fat). Here's where you are today:

Calories 1,090 / 2,100

Protein 102 / 150 g

Carbs 128 / 220 g

Here's my dinner — what's in it?

Looks like grilled salmon with rice and broccoli — logged to dinner, around 540 kcal (38g protein, 45g carbs, 20g fat).

Log this

Found it — Chobani Greek yogurt, 1 cup: 120 kcal, 15g protein. Which meal is this?

Breakfast Lunch Dinner Snack

Logged to snacks — 120 kcal, 15g protein.

Set my timezone to New York

Done — your days now roll over at midnight Eastern, so today's totals stay accurate wherever you are.

How am I doing on protein today?

You're at 118g of your 150g goal — 32g to go. A cup of Greek yogurt or a chicken breast would get you there.

Show my trends this week

You're averaging 1,980 kcal a day — about 5% under goal, protein's up 12g, and you're on a 6-day streak. Want it as a CSV?

Tracked so far, together

A growing global food log

— Food logs

— Calories tracked

— Protein

— Carbs

— Fat

Logged across 35 timezones worldwide

Everything, just by chatting

What you can track

Meals in plain language

Describe what you ate — your AI estimates calories, protein, carbs, and fat and logs it.

Scan a barcode

Snap or type a product barcode and pull verified macros from Open Food Facts, scaled to how much you ate.

Goals & progress

Set daily calorie, macro, and water targets and check live progress toward them.

Summaries & trends

Daily and weekly breakdowns, 7/14/30-day trends, streaks, and recurring meal patterns.

Water logging

Track hydration in milliliters alongside your meals and review it by day.

Timezone-aware

Days roll over in your local time, wherever you are in the world.

Export & own your data

Export everything to CSV anytime, and delete your account and data whenever you want.

Why Nutrition MCP

Talking beats tapping.

Snap a barcode or just say what you ate — no database digging, no separate app to open.

Traditional apps

Search a database for every item
Fix wrong database entries by hand
Yet another app, account, and paywall
Tedious manual logging

Nutrition MCP

Describe meals in plain language
Calories & macros estimated for you
Works inside Claude or ChatGPT, free
Ask for trends, summaries, and goals

Private by default Only you can see your data.

Open source Audit or self-host it.

Export anytime Your full history as CSV.

Delete instantly Remove your account & data.

Support

Help keep it running.

Nutrition MCP is free and ad-free. Patreon covers the server and database bills.

Free member

Follow along — get news and updates about the server, new tools, and what's coming next.

Follow on Patreon

Paid member

Pay what you want

Chip in for hosting and database costs so the server stays free and online for everyone.

Become a supporter

Start tracking in under a minute.

Free and open source — it works with the AI you already use.

Quick install Star on GitHub

Contact

Questions or feedback?

Found a bug, want a feature, or just have a question? Email me directly — I read every message.

anton@nutrition-mcp.com Send an email

FAQ

Frequently asked questions

What is Nutrition MCP?

Nutrition MCP is a free Model Context Protocol (MCP) server that lets you track meals, calories, macros, and nutrition history through natural conversation with Claude or ChatGPT. Instead of typing into a traditional app, you tell your AI what you ate and it logs everything for you.

What is the Model Context Protocol (MCP)?

The Model Context Protocol is an open standard that lets AI assistants like Claude and ChatGPT connect to external tools and data sources. An MCP server provides specific capabilities — here, nutrition tracking — that the AI can use during a conversation. Think of it as a plugin system for AI assistants.

Does it work with ChatGPT?

Yes. In ChatGPT on the web, open Settings → Apps, create a custom app with the server URL using OAuth, and sign in. It works on every ChatGPT plan.

Which other clients are supported?

Any MCP client that supports OAuth 2.0 with PKCE — including Claude.ai, the Claude desktop and mobile apps, Claude Code, Cursor, Windsurf, and VS Code.

Can I self-host it?

Yes. Nutrition MCP is open source (MIT). You can run your own instance with your own Supabase project — the GitHub repository includes a full self-hosting guide and a Dockerfile.

Is Nutrition MCP free?

Yes, it is completely free — no premium tiers, ads, or hidden costs. You just need a Claude or ChatGPT account to connect. Donations on Patreon help cover server costs.

What can I track?

Calories, protein, carbohydrates, fat, and water for every entry — described in plain language or pulled from a product barcode via Open Food Facts. You can view daily summaries, query meals by date range, update or delete past entries, set goals, and monitor trends over time.

Is my data private?

Your data is stored securely and linked to your personal account. Only you can access your nutrition history through your authenticated session. Nutrition MCP does not sell or share your data, and you can delete your account and all data at any time.