MyFitnessPal MCP Server
Click on "Install 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., "@MyFitnessPal MCP Servershow 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 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 |
| Read | Food diary (meals, entries, nutrition, totals, goals) for a date |
| Read | Search the MyFitnessPal food database |
| Read | Full nutrition breakdown for a food by MFP ID |
| Read | Recently used foods from the authenticated account |
| Read | Most-used foods from the authenticated account |
| Read | Foods created or saved by the authenticated account |
| Read | Body measurement history (Weight, Body Fat, ...) |
| Write | Log a body measurement for today |
| Read | Logged cardio/strength exercises for a date |
| Read | Daily nutrition goals |
| Write | Update daily nutrition goals |
| Read | Water intake for a date |
| Write | Log water intake for a date |
| Write | Add a food entry to a meal |
| Write | Update an existing diary entry by |
| Write | Delete an existing diary entry by |
| Read | Nutrition report (e.g. Net Calories) over a date range |
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- changemeal,quantity,unit(serving-size label, e.g."350 ml"), orweight_id(raw MFP serving-size option id, overridesunit) for an entry; requiresdatefor historical entries. MyFitnessPal can rewrite an entry during edit, so the response reportscurrent_entry_idandentry_id_changedso you can keep tracking the right row.mfp_delete_food_entry- delete an entry byentry_id(requiresdatefor historical entries).
Related MCP server: fitbit-googlehealth-mcp
Authentication: the cookie strategy
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 copiescookies.sqlite(and its WAL) to a temp file on each refresh - Firefox's locks don't matter - and extracts themyfitnesspal.comcookies. 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_FILEpointing at{"cookies": {name: value}}(AdamWalt's~/.mfp_mcp/cookies.jsonformat) 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 |
|
| Firefox profile dir (or parent dir of profiles) containing |
| - | JSON cookies file; used if set and no |
|
| Transport: |
|
| Bind address for HTTP mode |
|
| Port for HTTP mode |
| - | Comma-separated allowed |
| - | Shared passcode for the OAuth login page (remote connectors). Omit for unauthenticated LAN-only use |
| - | Exact public URL clients use (no path), e.g. |
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:latestCI 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, andMCP_OAUTH_PASSCODEset.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
/loginpasscode page once; enterMCP_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.
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/listcall 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).
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/delize/myfitness-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server