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
Quickstart
-
Connect your account (one-time; prompts you to paste a cookie — see
Authentication):
-
Add 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-mcp
Or install it as a plugin:
/plugin install myfitnesspal-mcp --marketplace Mason-Levyy/myfitnesspal-mcp
Claude 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, Codex CLI, Gemini CLI
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-mcp
Gemini CLI:
gemini mcp add myfitnesspal uvx mfp-mcp
-
Talk 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.com
- Copy the value of
__Secure-next-auth.session-token
- Paste it into the
mfp-mcp auth prompt, or on macOS run
mfp-mcp auth --clipboard and 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 auth
Then use the same --from 'mfp-mcp[autorefresh]' form in your client config
(e.g. uvx --from 'mfp-mcp[autorefresh]' mfp-mcp).
| Tool | What it does |
|---|
fitness_get_day | Nutrition totals, goals and remaining macros, diary entries, the MFP daily note, and feel note for a day |
fitness_search_food | Candidate matches with brand, calories, macros, serving, and ids |
fitness_draft_food | Numbered options with every serving size, filtered/ranked by optional calorie and macro targets |
fitness_log_food | Log a draft option (and serving), a remembered food, or exact ids to the real diary |
fitness_list_food_pins | Remembered query → food/serving choices (local) |
fitness_clear_food_pin | Forget one remembered choice, or all of them |
fitness_delete_food | Remove a diary entry by name match |
fitness_modify_food | Replace an entry (or change its quantity), choosing the replacement like fitness_log_food |
fitness_complete_day | Report whether a diary day is complete, mark it complete ("Complete This Entry"), or reopen it |
fitness_log_weight | Log a weight measurement (updates the same day on re-log) |
fitness_log_water | Add water (cups, fl oz, mL, L) or set the day's total with replace |
fitness_get_exercise | Read the exercise diary (cardio + strength) |
fitness_get_exercise_entries | List cardio and strength entries with each section's columns |
fitness_delete_exercise | Remove an exercise entry by name match (all_matches for multi-row sync cleanup) |
fitness_get_note | Read the MyFitnessPal daily diary note (the "Notes" box) for a day |
fitness_log_note | Write that daily note to MFP (replace, or append a new line) |
fitness_log_feel | Save a subjective "how I feel" note (stored locally, never sent to MFP) |
fitness_get_trends | One metric over a date range: weight, calories_in, protein, carbs, fat |
fitness_bulk_export | 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 8484
This 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 |
|---|
MFP_COOKIE | Session cookie (full header or bare token); overrides the saved file | – |
MFP_USERNAME | Your MFP username (not email); only needed if profile lookup fails | auto-detected |
MFP_IMPERSONATE | curl_cffi browser fingerprint (try chrome124 on 403s) | chrome |
MFP_SYNC_DAYS | Gap-fill lookback window in days | 30 |
MFP_MCP_DATA_DIR | 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-run
mfp-mcp auth, or set up auto-refresh.
- "couldn't read your MyFitnessPal profile": MFP's profile endpoint 500s
for some accounts. Set
MFP_USERNAME to 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_cffi session 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 with lxml.
- Writes replicate the web app's own XHR calls: the legacy food-search page
supplies the
food_id/weight_id that /food/add accepts, 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 pytest
Tests 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.