| FMRS | 51 / 100 · D | 77 / 100 · B | 75 / 100 · B |
|---|
| Reliability | 9 / 20 | 12 / 20 | 13 / 20 |
|---|
| Security and permissions | 8 / 20 | 16 / 20 | 12 / 20 |
|---|
| Maintenance | 10 / 20 | 16 / 20 | 16 / 20 |
|---|
| Documentation | 14 / 20 | 18 / 20 | 17 / 20 |
|---|
| Setup experience | 10 / 20 | 15 / 20 | 17 / 20 |
|---|
| Best for | - Individuals who want to view and organize MyFitnessPal food, exercise and weight records in natural language
- macOS Claude Desktop users who are comfortable authenticating with browser cookies
- People automating entries (e.g. inferring fasts from a sleep window plus first-meal timestamp) or correcting logs programmatically
- Technical users who accept a scraping-based approach and know the interface can break
| - Hevy PRO users who want AI assistants to directly access their workout data
- People who prefer using MCP clients like Claude, Cursor, Codex for fitness tracking
- Anyone needing summaries and insights from their training data
| - Scenarios needing clean, structured web context fed to an AI assistant
- Users already on the Firecrawl platform who want to call its scraping capability directly via MCP
|
|---|
| Not for | - Production use requiring official support or a stable public API
- Users unwilling to keep session cookies or account credentials on their machine
- Environments on Python 3.13+ or where lxml cannot be built
- MCP clients other than Claude Desktop (only a Claude Desktop config example is documented)
- Anyone who needs to read fasting history — MFP exposes no read endpoint for it
| - Users without a Hevy PRO subscription (API key required)
- Users who want to use the server without an API key
- Those needing delete workflows (Hevy API does not expose delete endpoints)
| - Simple static-page scraping where you don't want to depend on a third-party API and incur call costs
- Sites that explicitly disallow automated access (robots.txt)
|
|---|
| Required permissions | - Read and modify your MyFitnessPal account data (diary, goals, measurements, water, fasting)
- Write to ~/.mfp_mcp/cookies.json (mode 0600; equivalent to a password with full account access)
- On macOS, read each browser's '<Browser> Safe Storage' keychain entry to decrypt its cookie database
- Read browser cookies (Chromium-based or Firefox) or credentials from the MFP_USERNAME / MFP_PASSWORD environment variables
- Optionally read MFP_SECRET_KEY from the environment or OS keychain to decrypt credentials
| - Requires HEVY_API_KEY environment variable for Hevy API authentication
- Can create, update, and replace workouts, routines, folders, templates, and body measurements via tools
- Read operations can fetch workouts, routines, folders, templates, history, and user info
| - Requires a Firecrawl API key to call; cost and quota are governed by the Firecrawl account
- firecrawl_agent/firecrawl_interact perform automated browser interaction, which may trigger login or form-submission flows on the target site
|
|---|
| Risks and side effects | - The server can modify your diary, goals, measurements and water — mistaken calls change real data
- Session cookies grant full account access and are stored locally in ~/.mfp_mcp/cookies.json; leaking that file is leaking the account
- Storing plain credentials in the client config puts your MyFitnessPal password in plaintext on disk, readable by anything running as your user
- Reads and writes depend on MFP's undocumented interfaces, which can change without notice (the author notes it already happened once)
- Scraping and internal API use may conflict with MyFitnessPal's terms of service
- If MFP_SECRET_KEY is stored alongside the encrypted values in the same config file, the encryption provides little protection
| - API key can be misused if leaked; do not expose in URLs, logs, or screenshots
- Create operations may produce duplicates on retry; update operations replace existing records
- The server sends data to the Hevy API and may send telemetry to external services unless disabled
| - Bulk crawl/map tools can generate significant request volume against a target site — respect the site's rate limits and terms of service
- firecrawl_agent's interactive action chain is longer — define task boundaries clearly before running it to avoid accidentally triggering actions on a sensitive site
|
|---|
| Supported clients | Claude Desktop | Claude Desktop, Cursor, Codex, Google Antigravity | Claude Desktop, VS Code, Cursor, Windsurf, Zed, Amp |
|---|
| Tools | 20 | 26 | 11 |
|---|