What can you do with this server?

A remote MCP server for reading and managing MyFitnessPal diary, food, exercise, body measurements, nutrition goals, water, and nutrition reports. * Read a day's food diary with meals, entries, nutrition totals, and goals; JSON output includes diary entry IDs. * Search the MyFitnessPal food database, get detailed nutrition for a food, and list recent, frequent, or saved foods. * Add foods to the diary, update or delete diary entries, and create custom foods (private by default; public sharing is irreversible). * Read body measurement history and log a measurement for today. * Read logged exercises for a date, read/update daily nutrition goals, and read/set water intake. * Get nutrition reports over a date range. * Note: the README also mentions step counts, but mfp_get_steps is not present in the provided server schema.

How do I use MyFitnessPal MCP Server?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MyFitnessPal MCP Server show my food diary for today" 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.

MyFitnessPal MCP Server

by delize

Overview Schema Source Related Servers Discussions Admin

Python

Hybrid

MyFitnessPal MCP Service

A deployable Model Context Protocol (MCP) server for MyFitnessPal that works as a remote Claude connector: food diary, food search, exercises, body measurements, nutrition goals, water intake, and nutrition reports.

This is a fork of AdamWalt/myfitnesspal-mcp-python (MIT, tool implementations) restructured for remote deployment with the OAuth 2.1 / streamable-http transport skeleton from garmin-mcp-service. MyFitnessPal access is via coddingtonbear/python-myfitnesspal.

Tools

Tool	Type	Description
`mfp_get_diary`	Read	Food diary (meals, entries, nutrition, totals, goals) for a date
`mfp_search_food`	Read	Search the MyFitnessPal food database
`mfp_get_food_details`	Read	Full nutrition breakdown for a food by MFP ID
`mfp_get_recent_foods`	Read	Recently used foods from the authenticated account
`mfp_get_frequent_foods`	Read	Most-used foods from the authenticated account
`mfp_get_my_foods`	Read	Foods created or saved by the authenticated account
`mfp_get_measurements`	Read	Body measurement history (Weight, Body Fat, ...)
`mfp_set_measurement`	Write	Log a body measurement for today
`mfp_get_exercises`	Read	Logged cardio/strength exercises for a date
`mfp_get_goals`	Read	Daily nutrition goals
`mfp_set_goals`	Write	Update daily nutrition goals
`mfp_get_water`	Read	Water intake for a date, in ml
`mfp_set_water`	Write	Set the day's water total (`milliliters`, or legacy `cups`)
`mfp_add_food_to_diary`	Write	Add a food entry to a meal
`mfp_create_food`	Write	Create a new custom food in the MyFitnessPal database
`mfp_update_food_entry`	Write	Update an existing diary entry by `entry_id`
`mfp_delete_food_entry`	Write	Delete an existing diary entry by `entry_id`
`mfp_get_report`	Read	Nutrition report (e.g. Net Calories) over a date range
`mfp_get_steps`	Read	Daily step counts synced from Apple Health / devices

Food collections (recent / frequent / my foods)

mfp_get_recent_foods, mfp_get_frequent_foods, and mfp_get_my_foods each take an optional limit (recent/frequent default 10, my-foods default 100, max 100) and response_format (markdown or json). They intentionally use the legacy add-to-diary AJAX endpoints (/food/load_recent, /food/load_most_used, /food/load_my_foods) rather than the newer /food/mine, /meal/mine, or /food/new pages, which can redirect to /account/logout even when diary reads and API-token fetches still work.

Editing diary entries

mfp_get_diary with response_format=json now surfaces an entry_id for each meal entry. Pass that id to:

mfp_update_food_entry - change meal, quantity, unit (serving-size label, e.g. "350 ml"), or weight_id (raw MFP serving-size option id, overrides unit) for an entry; requires date for historical entries. MyFitnessPal can rewrite an entry during edit, so the response reports current_entry_id and entry_id_changed so you can keep tracking the right row.
mfp_delete_food_entry - delete an entry by entry_id (requires date for historical entries).

Creating a custom food

mfp_create_food submits a brand-new food to the MyFitnessPal database when mfp_search_food turns up nothing suitable. Required fields are description and the per-serving core macros (calories, fat, carbs, protein); brand, serving_size, servings_per_container, share_public, and the optional micronutrients (fiber, sugar, sodium, cholesterol, vitamins, etc.) round it out. All nutrition values are entered per single serving as defined by serving_size (e.g. serving_size="125 g" with the numbers for a 125 g portion). When the serving unit is a mass unit (g, mg, kg, oz, lb) the gram weight is recorded so MFP's gram-based scaling stays correct.

On success it returns the new food's mfp_id; pass that to mfp_add_food_to_diary to log it (it may take a short moment to also surface in mfp_search_food). Re-running with the same details creates duplicate foods.

share_public=True is irreversible — it submits the food to MyFitnessPal's shared public database, and public foods can no longer be edited or deleted. Leave it False (default) to create a private food you can still delete.

Implementation note: the python-myfitnesspal library's set_new_food() no longer works — MyFitnessPal replaced the server-rendered /food/new Rails form with a client-side SPA that has no authenticity_token input, so the library's HTML scrape raises IndexError: list index out of range. mfp_create_food instead POSTs to the v2/foods API with the account's bearer token (the same mechanism the library still uses for goals).

Related MCP server: MacroFactor MCP

MyFitnessPal's login page is captcha-protected, so headless password login is dead - this server never asks for your MFP password. Instead it reads session cookies from one of:

Firefox profile sidecar (recommended): log into myfitnesspal.com once, interactively, in a Firefox profile; mount that profile directory read-only into the container at /profile. The server copies cookies.sqlite (and its WAL) to a temp file on each refresh - Firefox's locks don't matter - and extracts the myfitnesspal.com cookies. The copy is cached and only re-read when the file changes, so Firefox can keep running (e.g. a headless Firefox sidecar container you occasionally VNC into to re-login).
JSON cookies file: MFP_COOKIES_FILE pointing at {"cookies": {name: value}} (AdamWalt's ~/.mfp_mcp/cookies.json format) or a plain {name: value} dict.

Session cookies expire eventually (~30 days); when tools start failing with auth errors, log into MFP again in that Firefox profile.

Environment Variables

Variable	Default	Description
`MFP_FIREFOX_PROFILE_DIR`	`/profile` (Docker)	Firefox profile dir (or parent dir of profiles) containing `cookies.sqlite` with a logged-in MFP session
`MFP_COOKIES_FILE`	-	JSON cookies file; used if set and no `cookies.sqlite` is found
`MCP_TRANSPORT`	`stdio` (`streamable-http` in Docker)	Transport: `stdio` or `streamable-http`
`MCP_HOST`	`127.0.0.1` (`0.0.0.0` in Docker)	Bind address for HTTP mode
`MCP_PORT`	`8000`	Port for HTTP mode
`MCP_ALLOWED_HOSTS`	-	Comma-separated allowed `Host` headers (reverse proxy domains). Enables DNS-rebinding protection; if unset, protection is disabled in HTTP mode
`MCP_OAUTH_PASSCODE`	-	Shared passcode for the OAuth login page (remote connectors). Omit for unauthenticated LAN-only use
`MCP_RESOURCE_URL`	-	Exact public URL clients use (no path), e.g. `https://mfp.example.com`. Required together with the passcode
`MCP_ACCESS_TOKEN_TTL`	`2592000` (30 days)	Access-token lifetime in seconds. When the token expires the connector re-authorizes, which means re-entering the passcode; a short value (the old 24h default) forces a daily re-login if the client doesn't silently refresh. Lower it (e.g. `86400`) for tighter tokens
`MCP_AUTH_MODE`	(unset)	`none`, `passcode_oauth` or `oauth`. Unset keeps the legacy behaviour above. For `oauth` (stateless Okta/JWT validation behind a gateway) and its `MCP_OAUTH_*` variables see Behind an MCP Gateway

Docker

docker build -t myfitnesspal-mcp-service .

docker run -d -p 8000:8000 \
  -v ~/.mozilla/firefox/abcd1234.default-release:/profile:ro \
  -e MCP_ALLOWED_HOSTS=mfp.example.com \
  -e MCP_RESOURCE_URL=https://mfp.example.com \
  -e MCP_OAUTH_PASSCODE="$(python3 -c 'import secrets; print(secrets.token_urlsafe(32))')" \
  ghcr.io/delize/myfitnesspal-mcp-service:latest

CI builds and pushes ghcr.io/delize/myfitnesspal-mcp-service (amd64 + arm64) on pushes to main and v* tags.

Claude Connector Setup

Same flow as garmin-mcp-service:

Deploy behind HTTPS (reverse proxy) with MCP_TRANSPORT=streamable-http, MCP_RESOURCE_URL, and MCP_OAUTH_PASSCODE set.
In Claude, add a custom connector with URL https://mfp.example.com/mcp. Leave OAuth Client ID/Secret blank - the server supports dynamic client registration (/register), authorization + PKCE (/authorize, /token).
Claude redirects you to the /login passcode page once; enter MCP_OAUTH_PASSCODE. After that the client holds and refreshes its own token.

The passcode proves "the caller knows the passcode", not identity - keep network-level access control (IP allowlist, VPN) in front of any internet-facing deployment. Omitting MCP_OAUTH_PASSCODE/MCP_RESOURCE_URL runs the HTTP server unauthenticated (a warning is logged); only do that on a trusted network.

Behind an MCP Gateway: External OAuth / Okta JWTs (`MCP_AUTH_MODE=oauth`)

The passcode OAuth server above keeps its issued tokens in memory, so every container restart invalidates every client's token. When the server sits behind an MCP gateway (e.g. LiteLLM) that obtains its own tokens from an identity provider, use MCP_AUTH_MODE=oauth instead: the server becomes a stateless OAuth 2.0 resource server that only verifies RS256 JWT access tokens issued by an external authorization server (Okta, or any issuer publishing a JWKS). Nothing is stored, so restarts are invisible to clients.

MCP_TRANSPORT=streamable-http
MCP_AUTH_MODE=oauth
MCP_OAUTH_ISSUER=https://your-org.okta.com/oauth2/default   # required
MCP_OAUTH_AUDIENCE=api://default                            # default; comma list allowed
MCP_OAUTH_REQUIRED_SCOPES=mfp.read                          # default; comma list, ALL required
MCP_OAUTH_ALLOWED_CLIENT_IDS=0oaXXXXXXXXXXXXXXXX            # optional; token's `cid` must be listed
# MCP_OAUTH_JWKS_URI=https://your-org.okta.com/oauth2/default/v1/keys   # default: ${issuer}/v1/keys
# MCP_OAUTH_CLOCK_TOLERANCE_SEC=30                          # default 30

Variable	Default	Meaning
`MCP_AUTH_MODE`	(unset)	`none`, `passcode_oauth` or `oauth`. Unset keeps the legacy behaviour (passcode OAuth if `MCP_OAUTH_PASSCODE`+`MCP_RESOURCE_URL` are set, no auth if neither is).
`MCP_OAUTH_ISSUER`	— (required)	Expected `iss`. Must be `https://` (plain `http://` only for localhost). Startup fails without it.
`MCP_OAUTH_AUDIENCE`	`api://default`	Accepted `aud` value(s), comma-separated.
`MCP_OAUTH_REQUIRED_SCOPES`	`mfp.read`	Scopes that must all be present in `scp` (or a space-delimited `scope`).
`MCP_OAUTH_ALLOWED_CLIENT_IDS`	(any)	If set, the token's `cid` (or `client_id`) must be one of these.
`MCP_OAUTH_JWKS_URI`	`${issuer}/v1/keys`	Where signing keys are fetched from (Okta's path by default).
`MCP_OAUTH_CLOCK_TOLERANCE_SEC`	`30`	Leeway for `exp`/`iat`/`nbf`.

Behaviour in oauth mode:

Only RS256 is accepted (HS*, none etc. are rejected before any key lookup).
Signing keys are cached for an hour; a token with an unknown kid triggers a refetch (key rotation), rate-limited to one refetch per 10s.
No Authorization header → 401 with WWW-Authenticate: Bearer realm="mfp-mcp".
Malformed header, bad signature, wrong iss/aud, expired, unknown kid, or a cid not in the allow-list → 401 with error="invalid_token".
Valid token missing a required scope → 403 with error="insufficient_scope".
The JWKS cannot be fetched and no key is cached → 503.
The built-in OAuth endpoints (/authorize, /token, /register, /revoke, /login, /.well-known/*) are not mounted (404), so there is a single auth path. MCP_OAUTH_PASSCODE/MCP_RESOURCE_URL are ignored.
Tokens are never logged.

The token's sub is not used for authorization - the server still acts as the single MyFitnessPal account behind its cookie source - but any token from the configured issuer/audience/client with the required scope is accepted. Per-user tokens (e.g. Okta Cross App Access / ID-JAG, where sub is the user's email) and machine tokens (client credentials) both work.

Okta setup: in your Okta custom authorization server, add a scope mfp.read and an access policy rule that lets the gateway's client obtain tokens with it (via Cross App Access for per-user tokens, or the Client Credentials grant for a machine token). Set MCP_OAUTH_ISSUER to that authorization server's issuer URL, MCP_OAUTH_AUDIENCE to its audience, and MCP_OAUTH_ALLOWED_CLIENT_IDS to the gateway's client id.

Migrating from passcode OAuth:

Set up the Okta scope/policy above and configure the gateway to send Authorization: Bearer <okta access token> to /mcp.
On this container set MCP_AUTH_MODE=oauth, MCP_OAUTH_ISSUER, MCP_OAUTH_AUDIENCE and (recommended) MCP_OAUTH_ALLOWED_CLIENT_IDS; remove MCP_OAUTH_PASSCODE/MCP_RESOURCE_URL/MCP_ACCESS_TOKEN_TTL (they are ignored in this mode).
Restart and check the logs: a missing or invalid MCP_OAUTH_* setting aborts startup instead of running without auth. Clients that used the passcode flow directly (Claude/ChatGPT connectors) must go through the gateway now.

docker run -d -p 8000:8000 \
  -v ~/.mozilla/firefox/abcd1234.default-release:/profile:ro \
  -e MCP_AUTH_MODE=oauth \
  -e MCP_OAUTH_ISSUER=https://your-org.okta.com/oauth2/default \
  -e MCP_OAUTH_AUDIENCE=api://default \
  -e MCP_OAUTH_ALLOWED_CLIENT_IDS=0oaXXXXXXXXXXXXXXXX \
  ghcr.io/delize/myfitnesspal-mcp-service:latest

Leaving MCP_AUTH_MODE unset keeps the old behaviour exactly. MCP_AUTH_MODE=none is an explicit opt-in to no auth; MCP_AUTH_MODE=passcode_oauth is the passcode server with both variables strictly required.

Local stdio use

For local stdio use (Claude Desktop):

{
  "mcpServers": {
    "myfitnesspal": {
      "command": "python",
      "args": ["-m", "myfitnesspal_mcp.server"],
      "env": {
        "MFP_FIREFOX_PROFILE_DIR": "/home/you/.mozilla/firefox/abcd1234.default-release"
      }
    }
  }
}

Troubleshooting

Tools don't appear even though the connector shows "Connected"

Problem: The connector authorizes and shows as Connected, but its tools never surface in a conversation - asking the model to use them, or searching for them, turns up nothing. No error is shown.

Cause: This is almost always a client-side tool-budget limit, not a problem with this server. Claude caps how many tools can be active in a single conversation across all connected servers combined. If another connector exposes a very large tool set, it can consume that budget and silently crowd this server's tools out of the conversation. (Seen in practice with a connector exposing ~170 tools starving this server's handful.)

Confirm / fix:

In a fresh conversation, disable the other large connector(s) and check whether these tools now appear. If they do, it was the budget.
Keep high-tool-count connectors in separate conversations, or trim their active tools if the client supports per-tool toggles.
This server always returns its full tool list regardless - you can verify independently with an authenticated tools/list call against /mcp. If that returns the tools but the client doesn't show them, the gap is on the client side, not here.

Attribution

Tool implementations: AdamWalt/myfitnesspal-mcp-python (MIT, this repo is a fork - full history preserved)
MyFitnessPal client library: coddingtonbear/python-myfitnesspal
OAuth/transport skeleton: garmin-mcp-service

License

MIT - see LICENSE (preserves the original copyright).

Available Tools

19 tools

mfp_add_food_to_diaryA

Add a food item to your MyFitnessPal food diary for a specific date and meal.

This tool adds a food entry to your diary. You can search for foods using mfp_search_food to find the food ID (mfp_id) needed for this tool.

Args: params: AddFoodToDiaryInput containing: - mfp_id (str): MyFitnessPal food item ID (from mfp_search_food) - meal (str): Meal name - 'Breakfast', 'Lunch', 'Dinner', or 'Snacks' (default: 'Breakfast') - date (str, optional): Date in YYYY-MM-DD format, defaults to today - quantity (float): Number of default servings for this food (default: 1.0)

Returns: str: Confirmation message with details of the added food entry

Inputs: params (required). Returns: result

mfp_create_foodA

Create a new custom food in the MyFitnessPal database (via the v2 API).

Use this when a food is not already in MyFitnessPal (mfp_search_food returns nothing suitable) and you want it available to log. All nutrition values are entered PER ONE serving_size (e.g. serving_size='125 g' with the numbers for a 125 g portion).

On success the new food's id is returned as mfp_id; pass it to mfp_add_food_to_diary to log the food (it may take a short moment to also surface in mfp_search_food). Calling this repeatedly creates duplicate foods.

IMPORTANT: share_public=True submits the food to MyFitnessPal's shared public database and is IRREVERSIBLE -- public foods can no longer be edited or deleted. Leave it False (default) to create a private food you can later delete.

Args: params: CreateFoodInput containing: - description (str): Food name (required) - brand (str, optional): Brand/manufacturer - calories, fat, carbs, protein (float): Core macros per serving (required) - saturated_fat, polyunsaturated_fat, monounsaturated_fat, trans_fat, fiber, sugar, sodium, potassium, cholesterol, vitamin_a, vitamin_c, calcium, iron (float, optional): Additional nutrients per serving - serving_size (str): Serving-size label, e.g. '1 Serving', '125 g' (default '1 Serving') - servings_per_container (float): Servings per container (default 1.0) - share_public (bool): Submit to the public database; irreversible (default False)

Returns: str: JSON confirmation including the new food's mfp_id

Inputs: params (required). Returns: result

mfp_delete_food_entryA

Destructive

Delete an existing MyFitnessPal diary entry.

Deletes a diary entry identified by the entry_id returned by mfp_get_diary (use response_format='json' to get the entry_id).

Args: params: DeleteFoodEntryInput containing: - entry_id (str): Diary entry ID from mfp_get_diary JSON output - date (str, optional): Date in YYYY-MM-DD format, defaults to today

Returns: str: Confirmation message with the deleted entry's name and meal

Inputs: params (required). Returns: result

mfp_get_diaryA

Read-onlyIdempotent

Get the food diary for a specific date including all meals and their nutritional information.

Returns meals (Breakfast, Lunch, Dinner, Snacks) with each food entry's name, quantity, and complete nutrition breakdown (calories, protein, carbs, fat, etc.). Also includes daily totals and goals.

Args: params: GetDiaryInput containing: - date (str, optional): Date in YYYY-MM-DD format, defaults to today - response_format (str): 'markdown' or 'json'

Returns: str: Formatted diary data with meals, entries, nutrition, and goals

Inputs: params (required). Returns: result

mfp_get_exercisesA

Read-onlyIdempotent

Get logged exercises for a specific date.

Returns both cardiovascular and strength training exercises with their details (duration, calories burned, sets, reps, weight, etc.).

Args: params: GetExercisesInput containing: - date (str, optional): Date in YYYY-MM-DD format, defaults to today - response_format (str): 'markdown' or 'json'

Returns: str: List of exercises with details and calories burned

Inputs: params (required). Returns: result

mfp_get_food_detailsA

Read-onlyIdempotent

Get detailed nutritional information for a specific food item by its MFP ID.

Returns complete nutrition breakdown including calories, macros (protein, carbs, fat), fiber, sugar, sodium, cholesterol, vitamins, minerals, and available serving sizes.

Args: params: GetFoodDetailsInput containing: - mfp_id (str): MyFitnessPal food item ID from search results - response_format (str): 'markdown' or 'json'

Returns: str: Complete nutritional information for the food item

Inputs: params (required). Returns: result

mfp_get_frequent_foodsB

Read-onlyIdempotent

Get most-used foods from MyFitnessPal.

This is backed by the legacy load_most_used endpoint exposed by the add-to-diary page.

Args: params: GetFoodCollectionInput containing: - limit (int, optional): Max results (default 10, max 100) - response_format (str): 'markdown' or 'json'

Returns: str: List of most-used foods

Inputs: params (required). Returns: result

mfp_get_goalsA

Read-onlyIdempotent

Get the user's daily nutrition goals (calories, protein, carbs, fat, etc.).

Returns the configured daily targets for all tracked nutrients.

Args: params: GetGoalsInput containing: - date (str, optional): Date in YYYY-MM-DD format, defaults to today - response_format (str): 'markdown' or 'json'

Returns: str: Daily nutrition goals and targets

Inputs: params (required). Returns: result

mfp_get_measurementsA

Read-onlyIdempotent

Get body measurements (weight, body fat, etc.) over a date range.

Returns historical measurement data with dates and values. Useful for tracking weight loss progress and body composition changes.

Args: params: GetMeasurementsInput containing: - measurement (str): Type of measurement (default 'Weight') - start_date (str, optional): Start date, defaults to 30 days ago - end_date (str, optional): End date, defaults to today - response_format (str): 'markdown' or 'json'

Returns: str: Measurement history with dates and values

Inputs: params (required). Returns: result

mfp_get_my_foodsA

Read-onlyIdempotent

Get foods created or saved by the authenticated user.

This uses the legacy load_my_foods endpoint from the add-to-diary page, which remains accessible even when the modern My Foods page redirects away from authenticated sessions.

Args: params: GetFoodCollectionInput containing: - limit (int, optional): Max results (default 100, max 100) - response_format (str): 'markdown' or 'json'

Returns: str: List of foods created or saved by the account

Inputs: params (required). Returns: result

mfp_get_recent_foodsA

Read-onlyIdempotent

Get recently used foods from MyFitnessPal.

Uses the legacy diary-add AJAX endpoint that still works when newer account pages like /food/mine redirect away from authenticated sessions.

Args: params: GetFoodCollectionInput containing: - limit (int, optional): Max results (default 10, max 100) - response_format (str): 'markdown' or 'json'

Returns: str: List of recently used foods

Inputs: params (required). Returns: result

mfp_get_reportA

Read-onlyIdempotent

Get a nutrition report over a date range.

Returns daily values for the specified nutrient/metric over the date range. Useful for analyzing trends and patterns in nutrition intake.

Args: params: GetReportInput containing: - report_name (str): Report type (e.g., 'Net Calories', 'Protein') - start_date (str, optional): Start date, defaults to 7 days ago - end_date (str, optional): End date, defaults to today - response_format (str): 'markdown' or 'json'

Returns: str: Daily values and summary statistics for the report period

Inputs: params (required). Returns: result

mfp_get_stepsA

Read-onlyIdempotent

Get daily step counts synced into MyFitnessPal (e.g. from Apple Health).

Returns one entry per day in the range. Days with no synced data have steps: null. Ranges are limited to 31 days per call.

Args: params: GetStepsInput containing: - start_date (str, optional): Defaults to 6 days before end_date - end_date (str, optional): Defaults to today - response_format (str): 'markdown' or 'json'

Returns: str: Daily step counts with a total/average summary

Inputs: params (required). Returns: result

mfp_get_waterA

Read-onlyIdempotent

Get water intake for a specific date.

MyFitnessPal's /food/water endpoint returns the amount in a field named milliliters (python-myfitnesspal's _get_water), so day.water is always ml regardless of the account's display unit.

Args: params: GetWaterInput containing: - date (str, optional): Date in YYYY-MM-DD format, defaults to today

Returns: str: Water intake amount for the specified date

Inputs: params (required). Returns: result

mfp_search_foodA

Read-onlyIdempotent

Search the MyFitnessPal food database for food items.

Returns a list of matching foods with their name, brand, serving size, calories, and MFP ID (which can be used with mfp_get_food_details).

Args: params: SearchFoodInput containing: - query (str): Search query (e.g., 'chicken breast') - limit (int): Maximum results to return (default 10) - response_format (str): 'markdown' or 'json'

Returns: str: List of matching food items with basic nutrition info

Inputs: params (required). Returns: result

mfp_set_goalsA

Idempotent

Update daily nutrition goals (calories, protein, carbs, fat).

Sets new daily targets for the specified nutrients. Only updates the values that are provided; others remain unchanged.

Args: params: SetGoalsInput containing: - calories (int, optional): Daily calorie goal - protein (int, optional): Daily protein goal in grams - carbohydrates (int, optional): Daily carb goal in grams - fat (int, optional): Daily fat goal in grams

Returns: str: Confirmation message with updated goals

Inputs: params (required). Returns: result

mfp_set_measurementA

Log a new body measurement (weight, body fat, etc.) for today.

Records the measurement value in MyFitnessPal for tracking progress.

Args: params: SetMeasurementInput containing: - measurement (str): Type of measurement (default 'Weight') - value (float): Measurement value (e.g., 185.5)

Returns: str: Confirmation message with the logged value

Inputs: params (required). Returns: result

mfp_set_waterA

Log water intake for a specific date.

Sets the day's total water. MyFitnessPal stores water in millilitres, so pass milliliters (preferred) or cups (converted at 236.588 ml/cup). The value replaces the day's total rather than adding to it.

Args: params: SetWaterInput containing: - milliliters (float, optional): Total ml for the day - cups (float, optional): Total US cups for the day - date (str, optional): Date in YYYY-MM-DD format, defaults to today

Returns: str: Confirmation message with the logged water amount

Inputs: params (required). Returns: result

mfp_update_food_entryA

Update an existing MyFitnessPal diary entry.

Supports changing the meal, quantity, serving size, and date for an entry previously returned by mfp_get_diary (use response_format='json' to get the entry_id). MyFitnessPal can rewrite an entry during edit and return a replacement row, so the response includes current_entry_id and entry_id_changed to keep callers tracking the right diary row.

Args: params: UpdateFoodEntryInput containing: - entry_id (str): Diary entry ID from mfp_get_diary JSON output - date (str, optional): Date in YYYY-MM-DD format, defaults to today - meal (str, optional): New meal name - quantity (float, optional): New number of servings - unit (str, optional): New serving-size label - weight_id (str, optional): Raw MFP serving-size option ID

Returns: str: Confirmation with the current entry id and whether it changed

Inputs: params (required). Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.9/5.0

Scored 2026-11-04 22:10 across 19 tools

Disambiguation4/5

Most tools target a distinct resource+action pair (water, steps, diary, measurements, goals, exercises, reports, food CRUD). The only real overlap cluster is mfp_get_recent_foods / mfp_get_frequent_foods / mfp_get_my_foods, which are all 'fetch a food collection' tools, though the descriptions do differentiate recent vs. most-used vs. user-created. mfp_get_diary vs. mfp_get_report is also a mild boundary (daily snapshot vs. range aggregation) but the descriptions clarify it.

Naming Consistency5/5

Every tool follows the mfp_<verb>_<noun> snake_case pattern (mfp_get_water, mfp_set_water, mfp_search_food, mfp_add_food_to_diary, mfp_delete_food_entry). Prefix, casing, and verb style are uniform across all 19 tools.

Tool Count4/5

19 tools is at the upper end but each maps to a real MyFitnessPal operation (diary CRUD, food lookup/collection, water, steps, measurements, goals, exercises, reports). A few food-collection variants could arguably be consolidated, keeping it from a perfect score.

Completeness4/5

Diary entries have full CRUD (get/add/update/delete), and water, measurements, and goals all have read+write coverage. Gaps exist: exercises and steps are read-only (no logging tool), and create_food implies custom foods are deletable but no delete-food tool is exposed, which is a notable dead end.

Maintenance

ActivityMaintained

ResponsivenessNo recent community issues

Resources

Related MCP Connectors

CoKarTa
io.github.AndresMuelas2004
Log meals and read your nutrition diary from Claude or ChatGPT.
Health & Wellness Note Taking
1
https://app.cokarta.com/mcp
Nexus
com.kushalsm.nexus
Calorie, workout and body-weight log inside ChatGPT and Claude. Log meals by text, photo or voice.
Health & Wellness Fitness Tracking Speech Processing
1
https://mcp.nexus.kushalsm.com/mcp
Kairo
com.kairocalories
Calorie tracker app for ChatGPT and Claude: read meals, macros, weight and log meals from chat.
Health & Wellness Fitness Tracking
1
https://mcp.kairocalories.com/mcp
Nutrition by Pack4BackB
com.pack4back
Log meals, water, and weight to Garmin Connect from Claude or ChatGPT.
Fitness Tracking Health & Wellness
121
https://nutrition.pack4back.com/mcp

Related MCP Servers

mfp-mcp
Health & Wellness Fitness Tracking
Mason-Levyy
A
license
A
quality
A
maintenance
Connect MyFitnessPal to Claude or any MCP client. Log meals, search food database with macros, track trends, and export nutrition history against your real MyFitnessPal diary.
Updated 7 days ago (2026-11-06 06:43 UTC)
18
620 PyPI
31
MIT
MacroFactor MCP
Health & Wellness Fitness Tracking
chaotix345
A
license
Not graded
quality
D
maintenance
Enables Claude.ai to read your MacroFactor nutrition data and log food back into MacroFactor.
Updated 4 months ago (2026-07-11 07:19 UTC)
1
MIT
fitness-mcp
Health & Wellness Fitness Tracking
ikeike443
A
license
Not graded
quality
C
maintenance
A personal remote MCP server that lets Claude read your Hevy workout data and MacroFactor nutrition data directly in conversation, with read-only tools for workouts, body measurements, macros, and weight trends.
Updated 10 days ago (2026-11-03 13:29 UTC)
MIT
MyFitnessPal MCP
Health & Wellness Fitness Tracking
a1dancole
A
license
Not graded
quality
C
maintenance
Enables Claude to access your MyFitnessPal diary—foods, portions, meal and daily nutrition totals, water, exercise, steps, and weight—through a custom connector on web, desktop, and mobile.
Updated 2 months ago (2026-09-01 09:23 UTC)
9 npm
MIT

MyFitnessPal MCP Service

Tools

Food collections (recent / frequent / my foods)

Editing diary entries

Creating a custom food

Authentication: the cookie strategy

Environment Variables

Docker

Claude Connector Setup

Behind an MCP Gateway: External OAuth / Okta JWTs (MCP_AUTH_MODE=oauth)

Local stdio use

Troubleshooting

Tools don't appear even though the connector shows "Connected"

Attribution

License

Available Tools

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

mfp-mcp

MacroFactor MCP

fitness-mcp

MyFitnessPal MCP

Behind an MCP Gateway: External OAuth / Okta JWTs (`MCP_AUTH_MODE=oauth`)