fitbithealthfitnessoauthsqlite
Queries Fitbit health data through MCP with OAuth, SQLite caching, incremental sync, and trend analysis.
Quick Install
Automated & IDE SetupCopy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.
Not yet automatically verified
This server is confirmed live — we successfully called its tools/list endpoint directly (see the verified badge above). We haven't yet sandbox-tested the stdio install command below specifically, which is a separate, ongoing check.
Manual Client & Custom JSON ConfigExpand JSON ▾
Client Config & Setup
Choose your client or environment
Target File:
💡 Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Overview
Use cases
Sync Fitbit history into a local SQLite cache
Query daily activity and sleep metrics through MCP
Compare monthly health and fitness trends
Inspect Fitbit device battery and synchronization status
Key features
OAuth 2.0 PKCE authentication
Local SQLite caching
Incremental and date-range synchronization
Live Fitbit API query mode
Health metric trend analysis
CLI authentication and import commands
Capabilities & Tool Schemas (18)
Inspect callable tools, capabilities, and parameters exposed to AI agents by Fitbit MCP.
fitbit_syncSync Fitbit health data to the local cache. Fetches data from the Fitbit API and stores it in SQLite for fast offline queries. Run this before using other fitbit_get_* tools. Syncs incrementally: only fetches data newer than the most recent entry in each table. First sync fetches the specified number of days. Args: data_types: What to sync. Options: "all", "heart_rate", "activity", "exercises", "sleep", "weight", "spo2", "hrv", "azm", "breathing_rate", "skin_temperature", "core_temperature", "cardio_fitness", "food_log". Comma-separated for multiple, e.g. "sleep,hrv". Default: "all". days: Days of history for first sync (default: 30). Ignored on subsequent syncs (uses last synced date). since: Optional "YYYY-MM-DD" backfill date. When set, fetches from this date regardless of what is already cached - use to pull history older than the current cache. Overrides incremental resume and days. until: Optional "YYYY-MM-DD" inclusive end date; requires since. Together they re-fetch and upsert exactly the since..until window - use to repair a gap in the middle of the cache without re-pulling everything from the gap to today. Returns summary of records synced per data type. Not for querying data - use fitbit_get_heart_rate, fitbit_get_activity, fitbit_get_sleep, etc. instead.
fitbit_get_activityGet daily activity summaries (steps, calories, active minutes, distance). Returns data from the local cache by default. Use live=True to fetch from Fitbit API. Run fitbit_sync first to populate the cache. Note: live=True fetches one API call per day - avoid large ranges to stay within the 150 requests/hour rate limit. Args: start_date: Start date as "YYYY-MM-DD", "YYYY-MM", or "30d". Default: last 30 days. end_date: End date as "YYYY-MM-DD". Default: today. live: If true, fetch directly from Fitbit API instead of cache. Returns one entry per day with steps, calories, active minutes, distance. active_minutes = very_active + fairly_active (excludes lightly active).
fitbit_trendsAnalyse trends in cached Fitbit data. Computes averages and totals over time from the local cache, auto-syncing if stale. Args: data_type: What to analyse. Options: "heart_rate", "activity", "exercises", "sleep", "weight", "spo2", "hrv", "azm", "breathing_rate", "skin_temperature", "core_temperature", "cardio_fitness", "food_log". Default: "activity". period: Aggregation period. Options: "weekly", "monthly", "quarterly". Default: "monthly". start_date: Start date as "YYYY-MM-DD" or "365d". Default: last 12 months. end_date: End date as "YYYY-MM-DD". Default: today. compare: Compare two periods. Format: "last_30d vs previous_30d", "2026-03 vs 2026-02", "2026-Q1 vs 2025-Q4". When set, period/start_date/end_date are ignored. Returns aggregated averages per period. For activity: steps, distance, active minutes. For exercises: sessions, duration, calories. For sleep: duration, efficiency, stage breakdown. For heart_rate: resting HR min/avg/max. For weight: weight, fat%, BMI. For spo2: avg/min/max oxygen saturation. For hrv: daily and deep RMSSD. Not for raw data - use fitbit_get_* tools instead.
fitbit_get_azmGet daily Active Zone Minutes (AZM) - Fitbit's headline cardio metric. AZM counts minutes spent in heart rate zones at or above Fat Burn intensity. Cardio and Peak zone minutes count double. Returns from local cache by default, auto-syncing if stale. Use live=True to bypass the cache. Args: start_date: Start date as "YYYY-MM-DD", "YYYY-MM", or "30d". Default: last 30 days. end_date: End date as "YYYY-MM-DD". Default: today. live: If true, fetch directly from Fitbit API instead of cache. Returns one entry per day with total_minutes plus per-zone breakdown (fat_burn_minutes, cardio_minutes, peak_minutes). Distinct from active_minutes in fitbit_get_activity, which counts wall-clock minutes regardless of intensity.
fitbit_get_breathing_rateGet nightly breathing rate (avg breaths per minute during sleep). Sourced during sleep tracking. Useful as an illness/recovery signal: sustained increases of 2-3 bpm above personal baseline can indicate incipient infection or strain. Returns from cache by default, auto-syncing if stale. Args: start_date: Start date as "YYYY-MM-DD", "YYYY-MM", or "30d". Default: last 30 days. end_date: End date as "YYYY-MM-DD". Default: today. live: If true, fetch directly from Fitbit API instead of cache. Returns one entry per night with breaths_per_min. Typical adult range: 12-20 bpm at rest.
fitbit_get_cardio_fitnessGet Cardio Fitness Score (VO2 Max estimate). Fitbit estimates VO2 Max from resting HR, HR during walks/runs, and demographics. Updates roughly weekly. Returns from cache by default, auto-syncing if stale. Args: start_date: Start date as "YYYY-MM-DD", "YYYY-MM", or "30d". Default: last 30 days. end_date: End date as "YYYY-MM-DD". Default: today. live: If true, fetch directly from Fitbit API instead of cache. Returns entries with vo2_max_low and vo2_max_high (mL/kg/min). Fitbit reports as a range (e.g. 39-43); when a single value is given, low and high are equal. Higher = better cardiorespiratory fitness.
How Fitbit MCP works
What partymola/fitbit-mcp MCP server does
The partymola/fitbit-mcp MCP server connects an MCP client to the Fitbit Web API and presents Fitbit health records as agent-callable tools. It covers daily activity, heart rate and zones, exercise sessions, sleep, weight, SpO2, HRV, Active Zone Minutes, breathing rate, skin-temperature variation, manually logged core temperature, cardio fitness, food and water logs, paired devices, activity goals, and lifetime statistics.
Most historical measurements can be synchronized into a local SQLite cache. Query tools then read from that cache by default, while a live option bypasses cached data and requests the Fitbit API directly. Trend analysis aggregates cached records weekly, monthly, or quarterly and can compare two periods.
The project is retired. Fitbit has stopped accepting new app registrations, and its Web API is scheduled to shut down on September 30, 2026. Existing installations may continue working until that date, but a new setup cannot be completed without an already registered personal Fitbit app.
How it works
Authentication uses OAuth 2.0 with PKCE, so the setup uses a Fitbit client ID rather than a client secret. Running the authentication command opens a browser, completes Fitbit authorization, and stores tokens locally. Access tokens last eight hours and refresh automatically; refresh tokens expire after 90 days of inactivity.
fitbit_sync performs the initial download and subsequent incremental updates. The first sync can cover a selected number of days, while later syncs resume from the newest cached record for each data type. A since date supports older backfills, and since combined with until can refresh a specific date window. Query tools can automatically sync when needed, or callers can run an explicit sync first.
Live requests are useful for current device state and uncached data, but some endpoints make one API request per day. The documented Fitbit rate limit is 150 requests per hour, so large live date ranges should be avoided.
Setup and configuration
The partymola/fitbit-mcp MCP server requires Python 3.13 or newer and a registered personal Fitbit developer app. The app must use http://localhost:8080 as its redirect URL. The client ID is needed for PKCE; the setup does not require the client secret.
Install the package with pip install fitbit-mcp or run it without installation using uvx fitbit-mcp. Run fitbit-mcp auth to authorize Fitbit, then start the stdio server with fitbit-mcp. Tokens are saved under ~/.config/fitbit-mcp/fitbit_tokens.json with restrictive file permissions. The command-line interface also provides doctor, sync, and JSON import commands.
A first sync is optional because query tools can populate the cache automatically. Use an explicit sync when you need more than the default initial history or want to select particular data types.
Tools and capabilities
Available capabilities include:
- Synchronize selected Fitbit data types into SQLite with incremental updates and date-range backfills.
- Query activity, exercise, sleep, weight, heart rate, HRV, SpO2, AZM, breathing rate, temperature, cardio fitness, and food-log records.
- Analyze cached metrics with period averages, totals, and comparisons.
- Inspect paired devices, battery information, and last sync times through a live-only tool.
- Retrieve live-only activity goals, lifetime totals, and personal-best records.
- Filter exercise results by a case-insensitive activity-name substring.
Sleep, HRV, SpO2, and other device-derived records can be sparse because they depend on tracking coverage. HRV and SpO2 endpoints require Fitbit Premium access. Food and water results only contain days logged in the Fitbit app.
Limitations and notes
This package cannot be newly configured from scratch after Fitbit stopped accepting app registrations. Its usefulness therefore depends on an existing registered personal app and continued Fitbit API availability. The API shutdown date is September 30, 2026.
The local database is specific to this project. The project documentation recommends copying fitbit.db before shutdown if retained Fitbit-only fields are needed. The suggested replacement, google-health-mcp, reads history from Google rather than importing this cache, and some fields do not have equivalent coverage there. This server is also not a medical diagnostic system: Fitbit measurements such as SpO2, breathing rate, temperature variation, and recovery metrics should be interpreted as recorded device or user-entered data.
Related MCP Servers
Adoption & maintenance
Factual signals from GitHub, npm, and our automated checks — not a rating.
GitHub stars
2
Stargazers on the source repository.
npm downloads
64
Package downloads in the last 30 days.
Last commit
11d ago
Most recent push to the default branch.
Tools exposed
18
Callable tools this server registers over MCP.
Directory activity
3 views
Config copies, upvotes, and views on AllMCPs.
Reviews
No reviews yet — be the first to share how this listing worked for you.
Frequently Asked Questions about Fitbit MCP
AllMCPs Directory Badge
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
Badge Style:
Live Dynamic SVG Preview
Markdown (GitHub README)
[](https://allmcps.com/mcp/partymola-fitbit-mcp)HTML Embed
<a href="https://allmcps.com/mcp/partymola-fitbit-mcp"><img src="https://allmcps.com/api/badge/partymola-fitbit-mcp?style=directory" alt="Fitbit MCP on AllMCPs" /></a>Technical Specs & Signals
CategorySports
PricingFree
10/11 checks healthy over the last 32d
63Quality signal: Good · 63/100How this signal is calculated ▾
Server availabilityNot measured
Not scored for repo-hosted servers — we can't reach the running server, only its GitHub page. Hosted MCP endpoints are health-checked live.
Verified ownership10/20
Documentation & tools30/30
Adoption & activity7/15
Community engagement0/10
A guidance signal from public completeness & health data — not a user rating. New listings start lower and rise as they add docs, get verified, and grow adoption. Signals we can't observe for a listing are skipped, not counted against it.
Supply-chain signal
No high-severity advisories surfaced by our automated scan.
Critical 0High 0Medium 0Low 0
Scanned 19d ago via OSV.dev · fitbit-mcp (PyPI)
Own this project?
This directory is pre-filled from public sources. Claim via GitHub README, site badge, or DNS TXT to unlock edit access and the Official badge — proof is checked automatically, then reviewed by our team.
Free dofollow backlink: add your website and place the AllMCPs badge on it — no claim needed. We detect it automatically and keep it verified as long as the badge stays live.
Claim & get free dofollowShare & Embed
Add our SVG badge (dark/light directory styles) or embeddable widget to your site.