MCP server for MyFitnessPal - full CRUD over food diary, custom foods, saved meals, recipes, exercise, measurements, and nutrition goals
Server has 25 tools with consistent naming (verb_noun pattern) and descriptions present for all. However, parameter descriptions are sparse or generic, output schemas are not documented, and error handling lacks recovery guidance. Most tools fall into the 'fair' range (60-69). Naming is strong (all start with action verbs: get_, add_, list_, remove_, create_, edit_, search_, delete_). Descriptions average ~80 chars, below the 194-char baseline for A+ tools. Parameter descriptions exist but are minimal (e.g., 'The ID of the food to add' for food_id). No documented output schemas, pagination guidance, or error recovery paths. Security concern: credentials handled via environment variables and keyring (good), but no explicit permission gates or audit trail declarations in tool definitions.
Add an exercise to the user's diary
Add a food to the user's diary for a specific date and meal
Add a body measurement for the user
Add water intake to the user's diary
Log foods across multiple days
Create a custom food with nutritional information
Create a saved meal from food components
Output schemas not documented. Tools return data but LLMs cannot predict field names, types, or structure. Breaks downstream tool chaining and forces agents to guess at response format.
Parameter descriptions are minimal (avg 30-40 chars vs 72-char baseline). E.g., 'The ID of the food to add' lacks context on format, constraints, or when to use. LLMs cannot infer valid ranges or formats.
No pagination or result limits documented. list_diary_entries, list_exercises, list_meals could return unbounded results, risking context window exhaustion. No limit, offset, or cursor parameters visible.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 55 | <=2025-11-25 | v2 |
Delete a saved meal
Edit a logged diary entry to change servings or meal
Edit an existing custom food in place
Edit a saved meal by rebuilding it
Get the user's diary settings
Search for a food by name and return matching foods with nutritional information
Get the user's body measurements for a date range
Get the user's nutrition goals
Get the user's water intake for a specific date
List all food entries in the diary for a specific date
List exercises logged for a specific date
List all saved meals
Log a meal's component foods to the diary
Remove an exercise from the diary
Remove a food entry from the diary
Rename the diary meal slots
Search for exercises by name
Set the nutrients shown in the diary (up to 6)
Error handling lacks recovery guidance. No visible error messages, categorization (retryable vs fatal), or actionable next steps. Agents cannot self-correct on invalid input.
Destructive tools (remove_food_entry, remove_exercise, delete_meal) lack confirmation or dry-run support. Agents can irreversibly delete data without safeguards.