An http streamable MyFitnessPal MCP server, to access your nutrition data on the go
概览
A deployable Model Context Protocol (MCP) server for MyFitnessPal that works as a : 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. 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 (/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. mfp_get_diary with response_format=json now surfaces an entry_id for each meal entry.
README
以下为原文 README 节选，完整内容请查看原文。
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:
安装
docker run -d -p 8000:8000 \配置
{
"mcpServers": {
"myfitnesspal": {
"command": "python",
"args": ["-m", "myfitnesspal_mcp.server"],
"env": {
"MFP_FIREFOX_PROFILE_DIR": "/home/you/.mozilla/firefox/abcd1234.default-release"
}
}
}
}