fatsecret-mcp
A self-hosted MCP server that lets Claude/ChatGPT read and update your FatSecret food diary through draft-and-confirm tools.
Search FatSecret catalog foods with servings, calories, and macros.
Read one diary day with meals, totals, targets, and remaining calories/macros.
Summarize daily totals for a period of up to 31 days.
Draft new food entries from catalog matches, nutrition labels/photos, or earlier diary entries without writing anything.
Confirm an approved draft to save entries to the diary.
Repeat earlier meals, scaling amounts in grams or ml.
Edit or remove existing diary entries, including entries logged in the FatSecret app.
Log missing branded products as stand-ins using nutrition-label values.
Support multiple household users, each signed in to their own FatSecret account.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@fatsecret-mcp log this photo as lunch"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
fatsecret-mcp
Log food to your FatSecret diary by talking to Claude or ChatGPT on your phone. You see a draft first, and nothing is saved until you say yes.
https://github.com/user-attachments/assets/44dfd991-5434-47ad-8b84-bcad24415a1f
A photo of dinner, the draft Claude proposes, a "yes", the day so far, and the new entry in the FatSecret app.
fatsecret-mcp is a self-hosted MCP server. It connects Claude, or ChatGPT when the Operator turns it on, to your own FatSecret food diary, the one you see in the FatSecret app. Claude can read a day or a few weeks of it against your daily calorie and macro targets. It can find foods in the FatSecret catalog and draft entries from a description or a photo. Each draft shows the amounts, calories, macros, a suggested meal and how your day looks after adding it. When a packaged product isn't in the catalog, a photo of its nutrition label is enough. A wrong entry can be fixed or removed the same way, through a draft.
One server serves a household: a few people, each signed in with their own FatSecret account. There's no public instance, so you run your own.
This project is unofficial. It is not affiliated with or endorsed by FatSecret, Anthropic or OpenAI, and it is not medical or dietary advice.
Powered by fatsecret Platform API
What you can ask
The server gives Claude five tools. You never call them yourself; you just talk.
search_foods
Finds foods in the catalog with servings that can be logged.
You: How many calories are in a cup of cooked jasmine rice?
Claude: FatSecret has "Jasmine Rice (cooked)": 1 cup (158 g) is 205 kcal, 4.3 g protein, 0.4 g fat, 44.5 g carbohydrate.
draft_entries
Proposes entries without writing anything.
You: (photo of a plate) Log this as lunch.
Claude: Here's the draft for lunch today:
Beef bibimbap, 480 g (1 bowl): 640 kcal, 32 g protein, 21 g fat, 80 g carbohydrate
I assumed one restaurant-sized bowl. After adding it you'll be at 1,420 of 2,200 kcal and 78 of 140 g protein. Save it?
A portion of known weight, such as a bowl or a roll, is saved in grams when the food can be measured in grams, so the FatSecret app shows the same amount as the draft.
confirm_draft
Writes the draft you approved.
You: Yes.
Claude: Saved. Beef bibimbap is in your FatSecret diary under lunch.
get_diary_day
Reads one day with its totals and what's left of your targets.
You: How much is left today?
Claude: You've had 1,420 kcal. 780 kcal are left, along with 62 g protein, 18 g fat and 95 g carbohydrate.
get_period_summary
Reads daily totals for up to 31 days.
You: How did my week go compared with the week before?
Claude: This week you averaged 2,050 kcal and 128 g protein a day; last week 2,240 kcal and 117 g protein. You went over your calorie target on two days this week, and on four the week before.
The numbers above are illustrative.
Related MCP server: indian-food-nutrition-mcp
How a meal gets logged
sequenceDiagram
actor U as You (Claude app)
participant C as Claude
participant S as fatsecret-mcp
participant F as FatSecret API
U->>C: photo + "log this as lunch"
C->>S: search_foods
S->>F: foods.search, food.get
C->>S: draft_entries
S-->>C: draft (amounts, kcal, macros, meal, the day after adding)
C-->>U: shows the draft
U->>C: "yes"
C->>S: confirm_draft(draft_id)
S->>F: food_entry.create, one per item
S-->>C: saved entriesThe draft is signed by the server and expires after thirty minutes. It can only be confirmed by the person it was made for. In Claude's connector settings, keep confirm_draft on "Needs approval" so that every write asks you first.
Products the catalog doesn't have
A free FatSecret API key reaches only the US catalog, in English. Most local and branded products aren't in it. For those, Claude asks for a photo of the nutrition label, or you type its values. The server logs the product as a stand-in: the closest catalog food, in the amount whose calories match the label, under the product's own name.
flowchart TD
S[Claude searches the catalog] --> Q{Found?}
Q -- yes --> E[Normal food entry]
Q -- no --> P["You send a photo of the label<br/>or type its values"]
P --> V[Claude reads the calories and macros]
V --> M["The server picks the closest catalog food<br/>and sets the amount so calories match"]
M --> N[Entry saved under the product's own name]Calories match the label exactly, but macros are only close, and sometimes noticeably off. This comes from translating a product outside the US catalog into a US one. A diary entry can't carry its own calories or macros; it only points at a catalog food and takes that food's values. A free key can't create foods, so the server picks the US food whose macros are nearest to the label. Your product's exact macros usually exist nowhere in the US catalog, so there's nothing closer to pick. The draft shows the label's values, the logged ones and the difference before you confirm, and opening the entry's details in the FatSecret app shows the catalog food underneath.
The server rejects a label whose calories don't roughly agree with its macros, which catches a misread photo or kJ taken for kcal. It doesn't remember stand-ins: next time, Claude reuses the label from the conversation or asks again. Repeating a stand-in from your diary keeps its name and its approximate macros.
If you log a product often, adding it once in the FatSecret app gives you exact values there. After that, Claude can repeat it from your diary.
Repeat an earlier meal
You: The same as yesterday's breakfast.
Claude: Yesterday's breakfast was:
Rolled oats, 80 g: 300 kcal
2% milk, 250 ml: 125 kcal
Greek yoghurt, 150 g: 90 kcal
Was it all the same today, or should I leave something out or change an amount?
You: Without the yoghurt, and half the milk.
Claude: Here's the draft, repeated from yesterday: rolled oats, 80 g, and 2% milk, 125 ml, 362 kcal in all. Should it go under breakfast today? Then I'll save it.
Claude reads the earlier day and drafts the entries you keep, without searching the catalog. The server copies each entry's food, serving, name and nutrition from your diary and scales them when you change an amount, always shown in grams or ml. It also works for products the catalog can't return, such as ones you added in the FatSecret app, and for stand-ins, which keep the product's name and don't need the label again. An amount that wasn't logged in grams or ml, such as "2 slices", is looked up once to show it in grams; when no weight is known, the entry is repeated as it was.
Fix or undo an entry
You: (right after saving) Undo that.
Claude: Here's the draft: remove beef bibimbap, 480 g, 640 kcal, from today's lunch. You'd be back at 780 of 2,200 kcal. A removed entry can't be restored, only logged again. Remove it?
You: Actually, keep it, it was just 300 g.
Claude: Here's the new draft: beef bibimbap, 480 g → 300 g, 640 → 400 kcal, still under lunch. Save the change?
A draft can also change entries already in your diary, including ones you logged in the FatSecret app: a new amount in grams or ml, another meal on the same day, or a new name. It can remove them too. Each change shows the entry before and after, and how each day looks afterwards. Nothing changes until you say yes. For "undo that", Claude removes the entries the last save wrote. For anything else, it reads the day first and asks when it's unclear which entry you mean.
FatSecret can't move an entry to another food or another day. So "it was chicken thigh, not breast" or "that was yesterday" becomes one draft that adds the right entry and removes the wrong one. The new entry is saved first, so if something fails halfway you see a duplicate rather than a gap. Changes reach back up to a year.
The FatSecret app in another language may open a US catalog entry without the serving it was saved in: an entry of "1 roll" can open as "1 gram". Saving it there may change the entry. Change such entries through Claude, or check the amount before saving in the app.
What it doesn't do
It can't look up barcodes, regional catalogs such as a Polish one, or custom foods. A free key reaches only the US catalog, so Claude searches it in English. Entries are still saved under the name you used, in your language, with a short note that the food was matched in the US catalog, such as "Kajzerka (katalog USA)"; the draft shows the catalog's name beside it.
It doesn't track weight, exercise or recipes, only food entries.
It doesn't serve strangers. There's no public server, and each server has a fixed list of people.
Run your own
A household server has one Operator, the person who deploys it and adds everyone else. Each person in the household signs in to FatSecret once through the Operator, then adds the server to their own Claude account as a custom connector, or to ChatGPT when the Operator turns it on.
flowchart LR
A["Anna's phone (Claude)"] --> CL[Claude connector]
J["Jan's phone (Claude)"] --> CL
CL -->|"each signs in with their own ID and password"| S[fatsecret-mcp on your server]
O[Operator] -->|"add-user, check"| S
S -->|"one FatSecret token per person"| F[FatSecret API]
F --> D[("each person's own diary, the same as in the FatSecret app")]You need:
your own FatSecret Platform API key. Register at platform.fatsecret.com; the free Basic plan is enough. Using it means accepting FatSecret's API terms. This project ships no keys;
a container host with HTTPS for the server, such as Railway;
a Claude or ChatGPT account for each person, with custom connectors available on their plan.
The short path:
Create a
.envwith your FatSecret key and a signing key, then runuvx --env-file .env fatsecret-mcp add-useronce per person (setup).Deploy the image
ghcr.io/jaronskijakub/fatsecret-mcpwith those values (deploy).In Claude, add
https://<your-server>/mcpas a custom connector and sign in (connector).
To try it on your own computer first, run it over stdio with Claude Code; setup covers that too. Request quotas, pacing and caching are described in limits, and the trust model in SECURITY.md.
Use it with ChatGPT
ChatGPT signs in the same way as Claude, with the same user id and connector password, and uses the same five tools. It's off by default. The Operator turns it on by setting FATSECRET_MCP_CLIENTS=claude,chatgpt and redeploying.
Each person then adds https://<your-server>/mcp in ChatGPT as a custom connector. ChatGPT offers custom connectors in developer mode, on some plans only; OpenAI's developer mode article lists them. Someone who uses both apps signs in to each one separately, and signing them out ends both (connector). The examples on this page come from Claude.
ChatGPT sometimes stops a confirmed change or removal with "This tool call was blocked by OpenAI's safety checks" before it reaches the server, while adding entries works. Nothing changes in your diary then. Try again in a new chat, or make the change with Claude or in the FatSecret app.
Documentation
Setup: configuration, adding people, their settings, and running it locally with Claude Code.
Deploy: Railway, other container hosts, Docker, and building the image yourself.
Connector: adding the server to Claude or ChatGPT, sign-in, and signing someone out.
Limits: the daily quota, pacing, search, drafts and input sizes.
Changelog: what changed in each version.
Report vulnerabilities through SECURITY.md, which also describes the trust model and what is stored where.
Roadmap
Custom foods for users with a FatSecret Premier key, so a branded product can be logged with exact values instead of a stand-in.
Open Food Facts lookups for products the US catalog lacks, by name or barcode.
Search your own foods by name. Anything in your diary can already be repeated from the day you logged it, but products you often log aren't searched yet; reading them from your whole diary took too many API requests, so this needs another approach.
Remember products logged from a label, so a stand-in doesn't need the photo again when it isn't repeated from your diary. This needs persistent storage.
Native confirmation dialogs in Claude for saving a draft, instead of a "yes" in the chat.
Development
uv sync
uv run ruff check && uv run ruff format --check
uv run pyright
uv run pytestThe tests never call FatSecret. They replay recorded responses from tests/fixtures/fatsecret/. An opt-in smoke test reads your real diary: FATSECRET_LIVE_SMOKE=1 uv run --env-file .env pytest tests/test_live_smoke.py. Container tests are described in deploy.
To release a version, set it with uv version X.Y.Z and in both places in server.json, and give it a dated entry in CHANGELOG.md; tests/test_package.py checks that they agree. Push that commit to main and wait for CI, which publishes its image. Then push the tag vX.Y.Z. The release workflow checks that CI passed on main for that commit, builds and checks the package, adds the version tag to the commit's image, publishes the package to PyPI and creates the GitHub release from the changelog entry. In a public repository it also publishes server.json to the MCP registry.
License
Available Tools
5 toolsconfirm_draftADestructive
Write a Draft to the User's Food Diary: its new Food Entries first, then its changes.
New entries go under the Draft's Meal and Diary Day. A removed entry can't be restored. Call this only after the User explicitly approved this Draft in their latest message. After a correction, draft again and confirm the new Draft instead. Confirm each Draft once: a repeat usually returns the earlier result, but after a server restart it would write the Draft again.
Inputs: draft_id (required). Returns: meal, status, changes, entries, +3 more
draft_entriesARead-only
Propose new Food Entries, and changes to logged ones, without writing to the Food Diary.
Show the Draft to the User.
A Food item uses Food and Serving ids from search_foods. number_of_units is the FatSecret unit count, not necessarily grams: scale it from the Serving's number_of_units. Name it with food_entry_name the way the User said it, in their language, followed by a short note in the same language that it was matched in the US catalog, e.g. "Kajzerka (katalog USA)" or "Kaiser roll (US catalog)". The Draft shows the catalog's name beside it. A Serving of known weight, such as "1 roll (57 g)", is logged as that weight in the Food's Serving in grams or ml when it has one, so the Draft may show that Serving instead.
A Nutrition Label item logs a branded product missing from the catalog as a Stand-in: the closest catalog Food for search_phrase, in the amount whose kcal match the label, under the product's name. Ask for a photo of the Nutrition Label unless the User already gave its values. For a product logged before as a Stand-in, reuse its label from this conversation or your memory, and ask again otherwise. Estimate the label, with estimated=true, only when the User has no packaging. Show the label values, the logged values and the difference. If the User dislikes the Stand-in, draft again with a different search_phrase.
A Diary Entry item logs a Food Entry from the Food Diary again, under its own name, with its Food, Serving and nutrition, so no catalog search is needed. For "the same as yesterday's breakfast", read that Diary Day with get_diary_day, list its Food Entries with their amounts to the User and ask whether everything was the same, or what to leave out or eat more or less of. Then draft the chosen entries by diary_day and food_entry_id, with metric_amount for a changed amount in grams or ml.
A change item changes or removes a Food Entry already in the Food Diary, by diary_day and food_entry_id: change="remove", or change="edit" with a new metric_amount in grams or ml, a meal on the same Diary Day or a food_entry_name. For "undo that" after a confirm_draft, remove the food_entry_ids it returned; undoing a change is a change back. For any other change, read the Diary Day with get_diary_day first, name the entries to change, and ask when it's unclear which one is meant. The Food or Diary Day of an entry can't change: for "chicken thigh, not breast", remove the entry and add a Food item; for "that was yesterday", remove it and add a Diary Entry item with the same food_entry_id, in one Draft whose diary_day is yesterday. Show each change before and after, and the removal_note when there is one.
A Draft holds at most 20 items: split a larger meal into several Drafts.
Include assumptions about estimated amounts. When the Draft has new items, always ask the User whether the suggested Meal is correct. If previous_day_suggested is true, ask whether to use Snacks on the previous Diary Day instead. meal and diary_day are for new items only. A correction needs a new Draft with the explicit Meal or Diary Day. Nothing is written by this tool; a Draft expires after thirty minutes.
Inputs: items (required), meal, diary_day. Returns: meal, items, totals, changes, +9 more
get_diary_dayARead-only
Read the User's Food Diary for one Diary Day.
Returns the Food Entries grouped by Meal (name, amount, kcal and Macros), the day's totals, the User's Daily Targets and what remains of them. Use it for questions like "what have I eaten today?" or "how much is left?". Past days reuse entries already read during this server session, for up to twelve hours. Today is always fresh. Set refresh=true when the User requests fresh data or says they changed this past day in the FatSecret app.
Inputs: refresh, diary_day. Returns: meals, totals, diary_day, remaining, +1 more
get_period_summaryARead-only
Read daily kcal and Macro totals alongside the User's configured Daily Targets.
Includes both endpoints, at most 31 Diary Days, and marks days without Food Entries. To compare two periods, call once for each period. Returns numbers without evaluation. Past days reuse Food Entries already read during this server session, for up to twelve hours. Missing days use FatSecret's month totals; today is always fresh. Set refresh=true when the User requests fresh data or says they changed these days in the FatSecret app.
Inputs: to_day (required), from_day (required), refresh. Returns: days, to_day, from_day
search_foodsARead-only
Find catalog Foods with loggable Servings, kcal and Macros.
Search one food at a time. Search a composed dish, such as a plate in a photo, as a whole first (e.g. "beef bibimbap"), and its components separately only when the dish has no good match. Pass the User's original description and, for non-English input, an English rendering: the catalog is searched with the English rendering, or the original when omitted. Nutrition and metric amounts describe the whole Serving; number_of_units is its FatSecret unit count. A not_found result is normal. When a branded product isn't among the matches, ask the User for a photo of its Nutrition Label and draft it as a Stand-in with draft_entries. This tool does not write to the Food Diary.
Inputs: description (required), english_rendering. Returns: status, matches, attribution
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
The tools mostly have distinct roles: search catalog foods, read one diary day, read period totals, draft changes, and confirm a draft. The main ambiguity is that draft_entries is an umbrella for adding, editing, removing, and re-logging entries, so its name undersells its scope, though it does not directly overlap with another tool.
All tool names use snake_case with a predictable verb_noun structure: get_diary_day, get_period_summary, search_foods, draft_entries, confirm_draft. The draft_entries/confirm_draft pair is slightly asymmetric in noun choice, but the overall convention is consistent and readable.
Five tools is a compact, well-scoped set for a food diary logging server, with clear separation between reading, searching, drafting, and confirming. Although draft_entries is dense, the overall count is appropriate and each tool earns its place.
The core diary lifecycle is covered: catalog search, daily diary reads, period summaries, drafting new entries and changes, and confirming writes. Minor gaps remain, such as no explicit target management and no multi-day entry-level read beyond period totals.
Maintenance
Related MCP Connectors
Log meals and read your nutrition diary from Claude or ChatGPT.
MyFitnessPal MCP server for ChatGPT, Claude and any AI agent: get diary day, search foods, log food, quick add calories, log water, log weight, log exercise and get nutrition goals in your own MyFitnessPal account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to MyFitnessPal yourself; Cotlet does not store your password and you need no MyFitnessPal API key. About the official MyFitnessPal API: MyFitnessPal has a private API and its API site says "We are not accepting requests for API access at this time" (checked 5 Nov 2026). There are no self-serve keys. Setup and FAQ: https://cotlet.dev/integrations/myfitnesspal-api-mcp-server
Calorie, workout and body-weight log inside ChatGPT and Claude. Log meals by text, photo or voice.
Calorie tracker app for ChatGPT and Claude: read meals, macros, weight and log meals from chat.
Related MCP Servers
- AlicenseAqualityCmaintenanceA filesystem-based MCP server that turns any MCP-capable AI agent into a conversational calorie and protein tracker with natural-language estimates, confidence-aware logging, daily/weekly progress, food-history search, and export, working offline with local fallback data.8MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that lets you log meals through Claude (and soon ChatGPT) in plain language, using India's official food composition data (IFCT 2017) plus USDA, enabling accurate calorie and macro tracking for Indian dishes with household units and photo logging.75 npm2AGPL 3.0
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol (MCP) server that connects AI assistants to your MyFitnessPal data, enabling reading food diaries, nutrition goals, weight measurements, and more via MFP's web scraping.MIT
- FlicenseNot gradedqualityCmaintenanceRemote MCP server for natural-language calorie/macro and weight tracking, designed to connect to Claude.ai as a custom connector.-