mfp-mcp-vercel
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-vercelwhat did I log for breakfast 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.
mfp-mcp-vercel
MyFitnessPal connector for Claude, running on Vercel. A thin wrapper around delize/myfitness-mcp (installed as a pinned dependency) that makes it work serverless:
Stateless OAuth (
stateless_oauth.py): client ids, auth codes and tokens are HMAC-signed payloads, so the connector stays authorized across restarts and redeploys.Stateless MCP transport (
app.py): fresh server task per request, JSON responses.Cookies from env: MyFitnessPal session cookies come from
MFP_COOKIES.
Environment variables
Variable | Required | Notes |
| yes | Passcode you type once when connecting Claude. Changing it revokes all tokens. |
| yes | Raw |
| no | Public base URL. Defaults to |
| no | Time zone for "today" in the diary. Default |
| no | Access token lifetime in seconds. Default 30 days. |
Env var changes need a redeploy to take effect.
Related MCP server: mfp-mcp
Connect Claude
Settings, Connectors, Add custom connector, URL https://<project>.vercel.app/mcp.
Leave client id/secret empty and enter the passcode on the login page.
Refreshing cookies
MyFitnessPal sessions expire (about 30 days). When tools start returning auth
errors: log into myfitnesspal.com, copy the Cookie request header again,
update MFP_COOKIES, redeploy.
Updating upstream
Bump the commit hash of myfitnesspal-mcp-service in pyproject.toml. app.py
overrides MCP SDK internals, so keep mcp pinned and retest when bumping it.
This server cannot be deployed
Maintenance
Related MCP Connectors
WHOOP recovery, strain, sleep and workouts in Claude via official WHOOP OAuth. Free, open source.
Calorie tracker app for ChatGPT and Claude: read meals, macros, weight and log meals from chat.
Garmin data in Claude & ChatGPT via the Garmin Health API. OAuth sign-in, no password sharing.
Pace is a remote MCP server that exposes wearable and fitness data to Claude via the Model Context Protocol. It connects to Garmin, Oura, Whoop, Polar, Fitbit and 20+ devices and provides 15 tools for querying sleep, activity, recovery, and training data. Hosted on Google Cloud Run, OAuth 2.1 authentication, Streamable HTTP transport. Instructions: First you need to create an account at: https://pacetraining.co and connect your wearables. After that you can connect the remote Server via Custom Connector in Claude and OAuth 2.1 Flow startet.
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables Claude to manage MyFitnessPal food diaries, nutrition goals, exercises, body measurements, and water intake via a remote MCP server using session cookie authentication.183MIT
- AlicenseAqualityAmaintenanceConnect 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.18214 PyPI26MIT
- AlicenseNot gradedqualityDmaintenanceEnables Claude.ai to read your MacroFactor nutrition data and log food back into MacroFactor.1MIT
- AlicenseNot gradedqualityBmaintenanceEnables Claude to act as a personal health coach by connecting to Garmin wearable data and Notion workspace for automated calorie tracking, photo food logging, and coaching insights.MIT