mfp-mcp
Connects an MCP client to your MyFitnessPal account to read and write diary, exercise, weight, water, notes, and nutrition trends.
Get daily nutrition totals, goals, remaining macros, food entries, MyFitnessPal daily note, and local feel note.
Search foods and draft/compare serving options by calories and macros before logging.
Log, modify, delete, and remember food diary entries across meals.
Log weight and water; read and delete exercise entries.
Read/write the MyFitnessPal daily note and save local-only feel notes.
Get metric trends and bulk-export date ranges.
Run via stdio or local streamable HTTP, using cookie-based authentication with optional session auto-refresh.
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., "@mfp-mcp log a banana as a snack"
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.
Log MyFitnessPal by talking to your AI.
Quickstart · Tools · Authentication · Changelog
MyFitnessPal MCP is a free, open-source MCP server that connects MyFitnessPal to Claude, Cursor, VS Code, or any MCP client. Log meals by talking, search the food database with macros, track trends, and export your nutrition history, all against your real MyFitnessPal diary.
Published on PyPI as mfp-mcp and in the
official MCP Registry
as io.github.Mason-Levyy/mfp-mcp.
Unofficial. MyFitnessPal has no public API; this reverse-engineers the web app's own endpoints. It can break whenever MFP changes their site. Use at your own risk, with your own account.
Why this one?
MyFitnessPal moved behind Cloudflare + NextAuth, which broke the username/password login that most existing integrations rely on. This server:
Authenticates with your browser session cookie over a real Chrome TLS fingerprint (curl_cffi), which passes Cloudflare
Auto-refreshes the session (optional): a headless browser profile rotates the token when it expires, and failed calls retry automatically
Writes, not just reads: log, modify, and delete real diary entries
Search-then-log: get candidates with macros, then log the exact item
Related MCP server: MyFitnessPal MCP Server
Quickstart
Connect your account (one-time; prompts you to paste a cookie — see Authentication):
uvx mfp-mcp authAdd the server to your client. The install buttons at the top do this in one click for Cursor and VS Code.
Claude Code
claude mcp add myfitnesspal -- uvx mfp-mcpOr install it as a plugin:
/plugin install myfitnesspal-mcp --marketplace Mason-Levyy/myfitnesspal-mcpClaude Desktop (
claude_desktop_config.json), Cursor (~/.cursor/mcp.json), Windsurf (~/.codeium/windsurf/mcp_config.json), and Cline (cline_mcp_settings.json) all take the same entry:{ "mcpServers": { "myfitnesspal": { "command": "uvx", "args": ["mfp-mcp"] } } }VS Code (or use the button above):
code --add-mcp '{"name":"myfitnesspal","command":"uvx","args":["mfp-mcp"]}'Codex CLI:
codex mcp add myfitnesspal -- uvx mfp-mcpGemini CLI:
gemini mcp add myfitnesspal uvx mfp-mcpTalk to it: "log a banana as a snack", "what did I eat yesterday?", "chart my weight this month".
Requires uv. Any MCP client that speaks stdio or streamable HTTP works, not just Claude.
Finding this useful? A ⭐ on GitHub helps other MyFitnessPal users find it.
Authentication
This server signs in with your browser's MyFitnessPal session cookie:
Log in at myfitnesspal.com
Open DevTools (F12) → Application (Chrome) or Storage (Firefox) → Cookies →
https://www.myfitnesspal.comCopy the value of
__Secure-next-auth.session-tokenPaste it into the
mfp-mcp authprompt, or on macOS runmfp-mcp auth --clipboardand copy the cookie: it connects as soon as the token reaches the clipboard
Sessions last 30 days from their last renewal. The server renews the session
whenever it builds a client and saves the cookies MyFitnessPal re-issues, so
the saved session stays current as long as it's used at least once a month.
mfp-mcp auth --check reports whether the saved session still works and
whether auto-refresh is set up; it renews and saves the session as it checks
and exits 1 when the session needs attention, so running it on a schedule
(cron, launchd) keeps an idle session alive and warns before it lapses.
Auto-refresh (recommended)
With the autorefresh extra, auth also seeds a persistent headless browser
profile. When MyFitnessPal rejects the session mid-call, the server tells your
client it is retrying, boots the profile headlessly, lets MyFitnessPal rotate
the session token, saves the fresh cookie, and retries the call.
uvx --from 'mfp-mcp[autorefresh]' playwright install chromium
uvx --from 'mfp-mcp[autorefresh]' mfp-mcp authThen use the same --from 'mfp-mcp[autorefresh]' form in your client config
(e.g. uvx --from 'mfp-mcp[autorefresh]' mfp-mcp).
Tools
Tool | What it does |
| Nutrition totals, goals and remaining macros, diary entries, the MFP daily note, and feel note for a day |
| Candidate matches with brand, calories, macros, serving, and ids |
| Numbered options with every serving size, filtered/ranked by optional calorie and macro targets |
| Log a draft option (and serving), a remembered food, or exact ids to the real diary |
| Remembered query → food/serving choices (local) |
| Forget one remembered choice, or all of them |
| Remove a diary entry by name match |
| Replace an entry (or change its quantity), choosing the replacement like |
| Report whether a diary day is complete, mark it complete ("Complete This Entry"), or reopen it |
| Log a weight measurement (updates the same day on re-log) |
| Add water (cups, fl oz, mL, L) or set the day's total with |
| Read the exercise diary (cardio + strength) |
| List cardio and strength entries with each section's columns |
| Remove an exercise entry by name match ( |
| Read the MyFitnessPal daily diary note (the "Notes" box) for a day |
| Write that daily note to MFP (replace, or |
| Save a subjective "how I feel" note (stored locally, never sent to MFP) |
| One metric over a date range: weight, calories_in, protein, carbs, fat |
| Whole date range in one call, including goals and remaining macros |
Logging flow
Food logging is draft-then-confirm, so what lands in your diary never depends on MyFitnessPal's search order:
fitness_draft_food("greek yogurt", min_protein=15, max_calories=150)returns numbered options. Each lists every serving size with calories and macros for the whole entry (serving × quantity) plus a suggested serving; options that meet the targets come first, near misses follow. Call it again with different targets to refine.fitness_log_food(draft_id=..., option=2, serving=1)logs exactly that food and serving, and remembers the choice for that query.Next time,
fitness_log_food(query="greek yogurt")logs the remembered food and serving without searching.
A bare fitness_log_food(query=...) with nothing remembered logs only when
exactly one result matches the name exactly; otherwise it logs nothing and
returns a draft to choose from. Remembered choices live in the local cache
(fitness_list_food_pins, fitness_clear_food_pin). Drafts expire after 24
hours.
fitness_modify_food picks the replacement the same way, before deleting
anything: a remembered food or a single exact-name match is used directly;
otherwise the entry is left alone and a draft comes back — call
fitness_modify_food again with the same query plus draft_id and
option.
fitness_log_food, fitness_delete_food, and fitness_modify_food all take
a meal argument the same way: breakfast/lunch/dinner/snacks, or the
literal name of any meal section currently on your diary — including a
renamed default meal or one of the up to two extra meals MyFitnessPal lets
you add in Diary Settings. Matching is case-insensitive against your
account's current meal labels. If you renamed a default meal, the keywords
still work: breakfast/lunch/dinner/snacks fall back to your first
through fourth meal, unless that slot now carries a different default name
(e.g. lunch won't land in a second meal you renamed to "Dinner"). Any other unrecognized meal raises an error instead
of silently logging into the wrong section.
Day summaries and trends read from a local SQLite cache that gap-fills from MyFitnessPal (first call on a fresh install fetches up to 30 days, one request per day).
Water logging reads the day's current total from /food/water, adds the requested
quantity, and posts the new total back to the same endpoint. Pass
replace=True to set the day's total outright (e.g. to fix a mislogged amount);
every call returns previous_ml, so a mistake can be reverted by passing it
back as amount with unit="ml" and replace=True. The separate
/stats request with a water_logged event is analytics telemetry; it does not
persist the water total.
Remote / HTTP mode
The default transport is stdio. For network clients:
mfp-mcp --http --host 127.0.0.1 --port 8484This serves streamable HTTP at /mcp. A session idle for 30 minutes is closed,
and the client has to reconnect; clients that keep the event stream open aren't
affected. There is no built-in authentication —
never expose it to the internet. Bind to localhost and front it with
something that authenticates for you: a VPN/tailnet (e.g. tailscale serve),
an authenticating reverse proxy, or an OAuth-aware MCP gateway.
Configuration
Variable | Purpose | Default |
| Session cookie (full header or bare token); overrides the saved file | – |
| Your MFP username (not email); only needed if profile lookup fails | auto-detected |
| curl_cffi browser fingerprint (try |
|
| Gap-fill lookback window in days |
|
| Where the SQLite cache + browser profile live | platform data dir |
Troubleshooting
403 / Cloudflare blocked: try
MFP_IMPERSONATE=chrome124(or another curl_cffi target). Datacenter IPs get challenged far more than residential ones."Session expired": confirm with
mfp-mcp auth --check, then re-runmfp-mcp auth, or set up auto-refresh."couldn't read your MyFitnessPal profile": MFP's profile endpoint 500s for some accounts. Set
MFP_USERNAMEto your username (not your email).curl_cffi install issues: prebuilt wheels cover Linux/macOS/Windows; musl (Alpine) builds from source.
FAQ
How do I connect MyFitnessPal to Claude? Run uvx mfp-mcp auth once to
save your MyFitnessPal session, then add the server: claude mcp add myfitnesspal -- uvx mfp-mcp in Claude Code, or the JSON entry from the
Quickstart in Claude Desktop. Then ask Claude to log a meal or
show yesterday's diary.
Is it free? Yes. It's open source under the MIT license, and it doesn't sell or collect anything.
Is there an official MyFitnessPal API? Not one you can use. MyFitnessPal's API is limited to approved partners and isn't open to new applications, so there's no API key to get. This server signs in with your own browser session cookie and makes the same requests the MyFitnessPal website makes (see How it works).
Which MCP clients does it work with? Any client that runs a stdio or
streamable HTTP server, including Claude Desktop, Claude Code, Cursor, Windsurf,
Cline, and VS Code. Use the uvx mfp-mcp command from the
Quickstart. AI coding agents can follow
llms-install.md.
Can it log meals as well as read them? Yes. It logs, replaces, and deletes diary entries, logs weight and water, and writes the daily note. See Tools.
Where does my data go? The server talks only to MyFitnessPal. The session cookie stays in your local config directory, and day summaries, feel notes, and remembered foods stay in a local SQLite file. Tool results go to whichever MCP client and model you connect it to.
How it works
Every request runs over a
curl_cffisession that impersonates Chrome's TLS fingerprint, so Cloudflare lets it through with just the NextAuth session cookie. The diary, exercise, and measurements pages are parsed withlxml.Writes replicate the web app's own XHR calls: the legacy food-search page supplies the
food_id/weight_idthat/food/addaccepts, deletes go through/food/remove, water reads/writes via/food/water, and the daily note reads/writes via/food/note— each with the page CSRF token.Day summaries, trends, and exports read a local SQLite cache that gap-fills missing days. The MyFitnessPal daily note syncs both ways; feel notes are local-only.
Development
git clone https://github.com/Mason-Levyy/myfitnesspal-mcp
cd myfitnesspal-mcp
uv sync --extra autorefresh
uv run pytestTests run against synthetic MyFitnessPal HTML/JSON fixtures — no account
needed. Lint and formatting are enforced with ruff (uv run ruff check .,
uv run ruff format .).
Contributing
Issues and pull requests are welcome, especially endpoint captures when MyFitnessPal changes something. See CONTRIBUTING.md for setup, style, and the PR checklist, and SECURITY.md for how to report vulnerabilities privately. Release history is in CHANGELOG.md.
Support the project
If this server saves you time, please star the repo. Stars are how other MyFitnessPal users find it in GitHub search and MCP directories. Bug reports and endpoint captures are just as welcome in issues.
Credits
The sign-in and the diary, exercise, weight, and food-detail parsing started as
python-myfitnesspal by
Adam Coddington, which this project used as a dependency through 0.4.x. That code
now lives in this repo, trimmed to what the server uses and adapted to its
curl_cffi session, under python-myfitnesspal's MIT license (see
NOTICE). Thanks to Adam and its contributors for years of keeping up
with MyFitnessPal's site.
License
MIT. Code adapted from python-myfitnesspal keeps its own MIT license notice in NOTICE.
Available Tools
18 toolsfitness_bulk_exportExport date rangeARead-only
Export a whole date range at once for analysis: per-day nutrition totals, food entries with macros, the MyFitnessPal daily note, and local feel notes. Read-only.
start/end: YYYY-MM-DD (default: last 30 days ending today). sync_first: gap-fill from MyFitnessPal before exporting. Off by default so large historical exports stay fast on cached data.
Inputs: end, start, sync_first.
fitness_clear_food_pinForget remembered foodADestructiveIdempotent
Forget a remembered food choice for query, or every choice with
clear_all=True, so the next log of that query drafts options again.
Inputs: query, clear_all.
fitness_delete_exerciseDelete exercise entryADestructive
Remove exercise-diary entries by name match (case-insensitive).
query: text matched against logged exercise names. By default deletes
exactly one entry, like fitness_delete_food: an exact name match wins;
otherwise several matches raise an error listing the candidates, and no
match raises an error listing what's actually logged. Of several identical
rows (same name and columns), one is removed.
all_matches: delete every entry whose name contains query — for
cleaning up syncs that log one workout as several same-named rows
(e.g. Garmin's "Aerobics, general"). Check fitness_get_exercise_entries
first; a short query can match many entries.
date: YYYY-MM-DD (default: today).
Inputs: query (required), date, all_matches.
fitness_delete_foodDelete food entryADestructive
Remove a food from the MyFitnessPal diary by name match.
query: text matched against logged entry names (e.g. "banana"). If this
matches nothing, the error lists what's actually logged that day/meal — use
that to retry with a better query. If it matches more than one entry (and
none is an exact name match), the error lists the candidates; narrow query
to pick one. Identical duplicates (same name, including its quantity, in
the same meal) are interchangeable, so one of them is removed; call again
to remove another.
meal: optional breakfast|lunch|dinner|snacks or any meal name on the
account, to disambiguate duplicates. date: YYYY-MM-DD (default: today).
Inputs: query (required), date, meal.
fitness_draft_foodDraft food entryARead-only
Draft a food entry: numbered options to choose from before logging.
Each option lists every serving size with its calories/protein/carbs/fat for the whole entry (serving × quantity) and a suggested_serving. The min_/max_ targets (grams; calories in kcal) also apply to the whole entry: options that fit come first, near misses follow, flagged fits_targets=false. A food you've confirmed before for this query is pinned to the top. The order is fixed once drafted.
Log a choice with fitness_log_food(draft_id=..., option=N, serving=M); call this again with different targets to refine. Drafts last 24 hours. date: YYYY-MM-DD (default: today).
Inputs: query (required), date, meal, limit, +9 more.
fitness_get_dayGet day summaryARead-only
Nutrition summary, diary entries, the MyFitnessPal daily note, and the local feel note for a day.
date: YYYY-MM-DD (default: today).
Inputs: date.
fitness_get_exerciseGet exercise diaryARead-only
Read the MyFitnessPal exercise diary (cardio + strength) for a day.
date: YYYY-MM-DD (default: today).
Inputs: date.
fitness_get_exercise_entriesList exercise entriesARead-only
List a day's cardio and strength exercise-diary entries.
Each entry has its section, name, and that section's columns (cardio: minutes, calories_burned; strength: sets, reps_set, weight_set). entry_id is informational only — fitness_delete_exercise deletes by name match. date: YYYY-MM-DD (default: today).
Inputs: date.
fitness_get_noteGet daily noteARead-only
Read the MyFitnessPal daily diary note (the free-text 'Notes' box at the bottom of the day) straight from your account.
date: YYYY-MM-DD (default: today).
Inputs: date.
fitness_get_trendsGet metric trendARead-only
A single metric over a date range, for charts/analysis.
metric: weight | calories_in | protein | carbs | fat. start/end: YYYY-MM-DD (default: last 30 days). Returns {metric, points: [{day, value}, ...]} with nulls omitted.
Inputs: metric (required), end, start.
fitness_list_food_pinsList remembered foodsARead-only
List remembered food choices (query → food and serving) that fitness_log_food reuses. Stored locally only.
Inputs: no named parameters.
fitness_log_feelSave feel noteBDestructiveIdempotent
Save a 'how I feel today' note. Stored locally only — never sent to MyFitnessPal.
rating: optional 1-5. date: YYYY-MM-DD (default: today).
Inputs: date, note, rating.
fitness_log_foodLog foodA
Log a food to the real MyFitnessPal diary.
Preferred: pick from a fitness_draft_food draft with draft_id + option (+ serving, default the option's suggested_serving). meal, quantity, and date default to the draft's. pin=True remembers the choice so logging the same query later reuses this food and serving.
With only query: logs a pinned food, or the single exact-name match;
otherwise nothing is logged and a draft is returned (needs_choice=true)
to pick from. With food_id + weight_id (from fitness_search_food): logs
exactly that item, query being its display name.
meal: breakfast|lunch|dinner|snacks (default breakfast) or any meal name on the account. quantity: number of servings (default 1). date: YYYY-MM-DD (default today).
Inputs: pin, date, meal, query, +6 more.
fitness_log_noteWrite daily noteADestructive
Write the MyFitnessPal daily diary note (the free-text 'Notes' box at the bottom of the day). This is your real MFP note, synced to your account — distinct from the local-only fitness_log_feel.
text: the note body. append: add to the existing note on a new line instead of replacing it. date: YYYY-MM-DD (default: today).
Inputs: text (required), date, append.
fitness_log_waterLog waterADestructive
Log water to the real MyFitnessPal water tracker.
amount: quantity to add to the day's total. unit: cup | fl_oz | ml | l
(common spellings like "cups", "oz", "fl oz", "milliliters", "litres" are
accepted). replace: set the day's total to amount instead of adding —
use it to correct a mislogged total (amount=0 clears the day).
Returns previous_ml; to undo a mistake, call again with
amount=previous_ml, unit="ml", replace=True.
date: YYYY-MM-DD (default: today).
Inputs: amount (required), date, unit, replace.
fitness_log_weightLog weightADestructiveIdempotent
Log a weight measurement to MyFitnessPal.
weight: in your MyFitnessPal account's display unit (kg or lbs). Logging twice for the same date updates that day's measurement. date: YYYY-MM-DD (default: today).
Inputs: weight (required), date.
fitness_modify_foodReplace food entryADestructive
Replace a MyFitnessPal diary entry: deletes the match, then adds a food.
query: the existing entry to replace (name match) within meal. If this
matches nothing, the error lists what's actually logged that day/meal — use
that to retry with a better query. If it matches more than one entry (and
none is an exact name match), the error lists the candidates; narrow query
to pick one. Of several identical duplicates, one is replaced.
new_query: the food to add instead; omit to re-add query (e.g. to change
quantity). The replacement is chosen like fitness_log_food's: a pinned
food or a single exact-name match is used directly; otherwise nothing is
changed and a draft comes back (needs_choice=true) — call again with the
same query plus draft_id + option (and optionally serving).
meal: breakfast|lunch|dinner|snacks or any meal name on the account,
used for both the delete and the add. quantity: servings (default 1, or
the draft's). date: YYYY-MM-DD (default: today).
Inputs: query (required), date, meal, option, +4 more.
fitness_search_foodSearch foodsARead-only
Search MyFitnessPal's food database and return candidate matches.
Each candidate has name, brand, calories, macros, serving, and the food_id + weight_id to pass to fitness_log_food to log exactly that item.
Inputs: query (required), limit, with_macros.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 18 tools
Most tools target a clearly distinct resource+action, and the food workflow (search -> draft -> log) is well delineated. However, fitness_get_exercise and fitness_get_exercise_entries both appear to read the same exercise diary and could easily be confused.
Every tool uses the same fitness_verb_noun snake_case pattern (get_day, log_food, delete_food, list_food_pins). No mixing of conventions.
18 tools is on the heavier side but each covers a genuine slice of the domain (food, exercise, notes, weight, water, trends, export, pins). Slightly over but defensible.
Strong coverage: full food CRUD plus search/draft/pins, water, weight, notes, trends, and bulk export. The only notable gap is adding exercise entries (read/delete exist, but logging appears handled by external sync), which agents can work around.
Maintenance
Related MCP Connectors
Calorie tracker app for ChatGPT and Claude: read meals, macros, weight and log meals from chat.
Calorie, workout and body-weight log inside ChatGPT and Claude. Log meals by text, photo or voice.
Log meals and read your nutrition diary from Claude or ChatGPT.
Track calories and macros right in Claude or ChatGPT and build a personal nutrition diary
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to read and write MyFitnessPal data, including food diary, exercises, body measurements, nutrition goals, and water intake.MIT
- AlicenseAqualityDmaintenanceEnables AI assistants to read and log MyFitnessPal nutrition data, including tracking calories, macros, searching foods, and adding meals through natural conversation.7MIT
- AlicenseAqualityCmaintenanceEnables AI assistants to interact with MyFitnessPal data including food diary, exercises, body measurements, nutrition goals, and water intake through natural language.2072MIT
- AlicenseAqualityBmaintenanceEnables Claude to manage MyFitnessPal food diaries, nutrition goals, exercises, body measurements, and water intake via a remote MCP server using session cookie authentication.194MIT