Yazio alternative
Yazio doesn't publish one you can connect — so you can't log your Yazio diary from Claude or ChatGPT. Nutrition MCP does the same job by conversation, and it's free and open source.
The short answer
The Model Context Protocol (MCP) is the open standard that lets AI assistants like Claude and ChatGPT connect to outside tools. Yazio doesn't publish a public MCP server, so there's no official way to log food to your Yazio diary from your AI. If you searched for “Yazio MCP” or “connect Yazio to Claude,” what you're really after is a nutrition tracker that lives inside your AI — that's exactly what Nutrition MCP is.
What you get instead
Say “oatmeal with banana and peanut butter” and your AI logs calories, macros, fiber, total sugar, caffeine, saturated and trans fat. Generic foods take their values from USDA FoodData Central when it has them, and estimates cover the rest; each number is tagged with where it came from. Log a meal ingredient by ingredient, or save the meals you eat often and log them again by name.
Send a product barcode and pull the label macros from Open Food Facts — fiber and sugar too, where the label lists them. Free for everyone, with no subscription.
Log body weight in kg or lb, and tape measurements of nine body sites in cm or in, set calorie, macro, saturated fat, fiber, sugar, caffeine, and water goals — fiber a target to reach, saturated fat, sugar and caffeine limits to stay under — and track trends toward a goal weight. Alcohol tracking is there too, opt-in and off unless you turn it on.
Ask for daily totals, weekly trends, streaks, and recurring meal patterns — right in the chat.
Import your meal history from another app's CSV export — parsed in your browser, not by the AI. Take everything back out whenever you want: one ZIP with your meals, saved meals, water, weight, body measurements, goals and profile, plus your account record, usage telemetry and connected apps, as CSV files. Meals are the only part that can be imported back in for now. Or delete your account, just as easily.
MIT-licensed and self-hostable — no ads, no paywall, no upsell. Audit the code or run your own instance.
Yazio vs. Nutrition MCP
Yazio is a polished tracker with good meal plans. Nutrition MCP focuses on effortless conversational logging that lives inside Claude or ChatGPT — free and open source.
Also compared: MyFitnessPal vs. Nutrition MCP · Cronometer vs. Nutrition MCP · Lose It! vs. Nutrition MCP · MacroFactor vs. Nutrition MCP · Lifesum vs. Nutrition MCP
Moving from Yazio
Yazio pairs tracking with structured meal plans, recipes, and fasting tools, polished for a European audience. If a guided plan is what keeps you on track, Yazio does that well and Nutrition MCP doesn't try to — it isn't a meal-plan app.
What it does do is make the logging half effortless. Instead of searching Yazio's database for each ingredient, you describe the dish and your AI handles the macros — then answers “how am I doing today?” in the same breath. Pair it with whatever eating plan you already follow.
This actually makes the two complementary rather than competing. Keep following a Yazio plan, or any plan, for the “what to eat” side; use Nutrition MCP for the “did I stay on track” side, logged by conversation and free. The one place it won't help is fasting timers — that's Yazio's territory, not a nutrition log's.
Your Yazio history
Ask to import and an importer opens right in the chat: pick your export, map the columns, preview what will be added, then confirm. The file is read in your browser — the AI never sees the rows. In clients without in-chat panels, paste your export instead.
Your Yazio history can come across, though you'll do a little of the work. Ask to import and an importer panel opens in the chat: you pick your CSV export, it's parsed in your browser, and you point its columns at date, food, meal, calories, protein, carbs, fat, fiber, total sugar, and caffeine yourself. Four apps' exports — MyFitnessPal, Cronometer, Lose It!, and MacroFactor — are recognised by their column names; Yazio isn't one of them, so expect to set that mapping once. Everything after it is the same: a preview of what will be added, then your confirmation.
The European quirks that defeat most importers are handled. A semicolon-delimited file whose numbers use comma decimals — the shape Excel produces in a German or Austrian locale — is read correctly, instead of the delimiter being mistaken for a decimal point or every macro being scaled by a thousand. The headings the mapper knows aren't English-only either: a German export's Datum, Kalorien, Eiweiss, Kohlenhydrate, Ballaststoffe, Zucker and Koffein are all recognised, and fiber, sugar and caffeine are matched in Spanish, French, Italian and Dutch as well — fibra, sucres, zuccheri, suikers, cafeína, caffeina — so a localised file often arrives part-mapped, leaving you fewer columns to set by hand. Quoted fields, line breaks inside a cell, blank-ish values, and stray totals rows are handled too, and the AI never reads the file, so no number can be mistyped in transit.
Dates and energy are confirmed rather than guessed. A DD/MM/YYYY column is read day-first, and where the values genuinely can't settle it — 05/06 being either May or June — the importer shows its reading beside a row from your own file so you can correct it. If the energy column is in kilojoules it's converted to kilocalories, with the unit shown as a control next to a worked example. Re-importing the same file adds nothing: each row carries a content fingerprint, so repeats come back as already logged as long as your timezone hasn't changed in between.
How to switch
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.
Using ChatGPT or another client instead? The full install guide covers ChatGPT, Cursor, VS Code, Claude Code, and more.
FAQ
Not an official one. Yazio doesn't publish a public Model Context Protocol (MCP) server, so there's no official way to log to your Yazio diary from Claude, ChatGPT, or other MCP clients. Some unofficial, community-built servers exist; they aren't made or supported by Yazio. Nutrition MCP is different: a free, open-source tracker built as an MCP server from the ground up, with its own account, that can import your Yazio CSV export.
There is no official Yazio connector for Claude, because Yazio publishes no public MCP server. One option is Nutrition MCP, a free MCP server listed in the Claude directory: open it at https://claude.ai/directory/nutrition-mcp, click Connect, sign in, and start logging by conversation.
No. Yazio's structured meal plans, recipes, and fasting tools are its strength, and Nutrition MCP doesn't try to replace them — it handles the logging half. Many people keep following their Yazio (or any) plan and simply log against it here for free.
Usually, yes. Rather than searching Yazio's database for each ingredient and setting portions, you describe the finished dish once — “a bowl of muesli with yogurt and berries” — and your AI logs the macros in a single step, using USDA values for generic foods where it has them and estimates otherwise.
If you want to track calories, macros — fiber, total sugar, caffeine, saturated and trans fat included — water, and weight without opening a separate app or tapping through a food diary, yes. You describe what you ate in plain language, send a photo, or scan a barcode, and your AI logs it. Generic foods take USDA FoodData Central values when it has them, packaged products come from Open Food Facts by barcode, and estimates cover the rest — completely free and open source.
Yes, using manual column mapping. Ask to import and an importer opens in the chat: you pick your Yazio CSV export, it's parsed in your browser rather than read by the AI, and you point its columns at date, food, meal, calories, and macros — fiber, total sugar and caffeine among them — yourself. Yazio isn't one of the four exports recognised by column name, so that mapping is a one-time manual step, though headings the mapper already knows (in German, and for fiber, sugar and caffeine in Spanish, French, Italian and Dutch too) fill themselves in. Semicolon-delimited European files with comma decimals, DD/MM/YYYY dates, and kilojoules are all handled, and re-importing the same file creates no duplicates as long as your timezone hasn't changed in between. In clients without in-chat panels you can paste your export instead.
Not when the importer opens. It parses the CSV in your browser and shows you what will be added before anything is written: how many meals, the calorie total, anything it had to flag, and the rows themselves — a long file lists the first of them plus a count of the rest rather than every line. Only the rows you confirm are sent, and they go as structured data rather than through the AI's reply, so no row can be mistyped or invented in transit. Each row also carries a content fingerprint, so running the same file again reports those meals as already logged instead of duplicating them, as long as your timezone hasn't changed in between. If your client can't display in-chat panels, the fallback is to paste the export — the AI does read it on that path, so prefer the importer when you have the choice.
Yes. Nutrition MCP is completely free with no premium tier, ads, or paywalled features — unlike apps that put some features behind a subscription. You need an AI app that supports MCP, such as Claude or ChatGPT, and a free Nutrition MCP account, which you create with Google or an email and password the first time you connect.
Free and open source — no Yazio account, no app to open.
Yazio is a trademark of its respective owner. Nutrition MCP is an independent, open-source project and is not affiliated with, endorsed by, or sponsored by Yazio. Comparisons reflect publicly available information at the time of writing and may change.