Fitbit MCP. Query sleep, heart rate, and activity trends in conversation.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Fitbit. Get all your health and fitness data via your AI client. Query sleep logs, heart rate trends, activity summaries, and nutrition intake—all in natural conversation.
You can track daily steps, see blood oxygen levels (SpO2), monitor weight changes, and check your deep sleep stages without opening the Fitbit app.
It brings your entire wearable history directly into your agent's context.
What your AI agents can do
Get activities date
Gets a summary of steps, calories, distance, and active minutes for one specific day.
Get activities timeseries
Gets detailed time series data for steps, calories, distance, and other activity metrics over a date range.
Get body weight
Gets your body weight, BMI, and fat percentage for a specified date.
Gets steps, calories, distance, and active minutes for a specific date.
Pulls detailed time series data for steps, distance, and calories across user-defined date ranges.
Retrieves sleep start time, duration, and minutes in deep, light, and REM stages for a specific night.
Queries resting heart rate and heart rate zones for a specific date or time period.
Retrieves average SpO2 percentage and its min/max values for a specific date.
Accesses total calories, macros, and water intake logs for a specific day.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
019d843bget activities date
Gets a summary of steps, calories, distance, and active minutes for one specific day.
019d843bget activities timeseries
Gets detailed time series data for steps, calories, distance, and other activity metrics over a date range.
019d843bget body weight
Gets your body weight, BMI, and fat percentage for a specified date.
019d843bget breathing rate
Gets your breathing rate in breaths per minute for a specific date.
019d843bget cardio fitness score
Gets your VO2 Max score and percentile ranking for a specific date.
019d843bget devices
Lists all connected Fitbit devices, showing their version, MAC address, and sync status.
019d843bget foods date
Gets a summary of calories consumed, macros, and water intake for one specific day.
019d843bget heart date
Gets your resting heart rate and heart rate zones for a specific date.
019d843bget heart timeseries
Gets resting heart rate and heart rate zones over a date range.
019d843bget profile
Retrieves your basic profile details like name, age, height, and gender.
019d843bget sleep date
Gets a detailed sleep log, including stages (deep, light, REM) and efficiency, for one specific night.
019d843bget sleep timeseries
Gets sleep summaries and stages over an extended date range.
019d843bget spo2
Gets your blood oxygen saturation (SpO2) percentage for a specific date.
019d843bget water
Gets your water intake volume and timestamps for a specific date.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Fitbit, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
Got your Fitbit account linked to your agent? You can pull every piece of health and fitness data you've collected without even opening the app. Your agent handles it all via natural conversation. You'll get a full history of your wearable data right into your context.
Activity Tracking
You can grab a summary of your daily steps, calories, distance, and active minutes for any single date using get_activities_date. If you wanna see how those numbers stack up over weeks or months, get_activities_timeseries pulls detailed time series data for steps, distance, and calories across a range of dates. You can also check your basic profile info, like name, age, height, and gender, with get_profile.
Sleep and Heart Rate
Need to know about your sleep? get_sleep_date gives you a deep dive into a single night's sleep, showing start time, total duration, and minutes spent in deep, light, and REM stages, plus the efficiency score. For long-term views, get_sleep_timeseries tracks those sleep summaries and stages over an extended date range.
You can monitor your heart health too. get_heart_date reports your resting heart rate and heart rate zones for a specific date, while get_heart_timeseries tracks those rates and zones over time. You'll also get your VO2 Max score and percentile ranking for a specific date using get_cardio_fitness_score.
Daily Metrics and Logging
get_spo2 retrieves your blood oxygen saturation (SpO2) percentage and its minimum and maximum values for a specific date. You can check your breathing rate in breaths per minute for a specific date using get_breathing_rate. To track what you eat and drink, get_foods_date gives you a summary of calories consumed, macros, and water intake for a specific day. get_water checks your water intake volume and timestamps for a specific date.
You can also check your body composition—weight, BMI, and fat percentage—for a specified date using get_body_weight.
System Checks
Want to know what's connected? get_devices lists every Fitbit gadget, showing its version, MAC address, and whether it's synced up.
How it works: You subscribe to this server, generate an OAuth2 access token from your Fitbit Developer Portal, and your AI client uses the tool names—like get_sleep_date or get_activities_timeseries—to pull your data.
How Fitbit MCP Works
- 1 Subscribe to the server and generate an OAuth2 access token from your Fitbit Developer Portal.
- 2 Pass the desired date or date range parameters (e.g., 'last night', 'last 7 days') to the agent's tool call.
- 3 The agent executes the tool, which returns the raw, structured data to your AI client for synthesis.
The bottom line is: your agent reads the raw data from Fitbit and structures it into plain text for you.
Who Is Fitbit MCP For?
The health enthusiast who doesn't want to open the Fitbit app just to check their sleep score. The physical therapist who needs longitudinal data on cardiac trends. The developer building biometric agents who need reliable, structured access to diverse time-series metrics. You're here because clicking through 10 different dashboards is too slow.
Checks get_sleep_date and get_activities_timeseries to spot patterns, like correlating poor sleep with low steps the next day.
Builds agents that pull get_cardio_fitness_score and get_heart_timeseries to calculate training load and recovery metrics.
Runs queries combining get_body_weight and get_spo2 to monitor changes in patient biometrics over a measured period.
What Changes When You Connect
- See deep sleep stages and total duration instantly. Instead of opening the Fitbit app to find your sleep score, your agent runs
get_sleep_dateand gives you the numbers right away. This saves minutes of dashboard clicking. - Track trends across weeks or months without manual export. Use
get_activities_timeseriesto pull steps and calories for a 30-day view, letting your agent spot dips or spikes you'd otherwise miss. - Correlate physical metrics effortlessly. You can combine
get_heart_date(resting heart rate) withget_activities_date(steps) in one prompt. The agent handles the data joins, not you. - Monitor advanced biometrics on demand. Use
get_spo2orget_breathing_rateto check blood oxygen or breathing rates without knowing the exact API endpoint. Just ask your agent. - Manage data flow from one place.
get_deviceslets you verify if your Fitbit sync is broken before you start an analysis. It tells you if the data you're about to pull is even current. - Get a full picture of daily intake. Use
get_foods_dateandget_watertogether to get a complete picture of your diet and hydration for a given day.
Real-World Use Cases
Tracking Recovery After a Marathon
A runner needs to know if they are ready for a long run. They prompt their agent: 'What was my sleep quality and heart rate last week?' The agent runs get_sleep_timeseries and get_heart_timeseries. It then compares the low sleep efficiency to the elevated resting heart rate, advising a rest day.
Analyzing Diet Impact on Energy
The user suspects their carb intake affects their activity levels. They ask their agent to run get_foods_date for the last 10 days and compare the total carbs to the daily get_activities_date (steps). The agent reports if high-carb days consistently show higher step counts.
Monitoring Chronic Conditions
A patient needs to track long-term SpO2 changes. They ask the agent to pull get_spo2 for the last three months. The agent presents the data trend, which the patient's care team can use for an informed consultation.
Routine Health Checkup Data Prep
The user asks the agent to compile all metrics for their doctor's visit. The agent sequentially calls get_profile for demographics, get_body_weight for weight, and get_heart_date for heart rate, giving a clean, comprehensive summary.
The Tradeoffs
Calling 14 tools sequentially
Manually running get_activities_date and then waiting for it to finish before running get_sleep_date, then waiting for that to finish, etc. This clogs your client and takes forever.
→
Let your AI client orchestrate the calls. Give the agent a single prompt: 'Compare my activity to my sleep over the last week.' The agent knows which tools (get_activities_timeseries and get_sleep_timeseries) to run in parallel and combine the results.
Forgetting the date parameter
Asking the agent 'Show me my heart rate trends.' The agent fails because it doesn't know if you mean 'today,' 'last week,' or 'last year.'
→
Be specific with your prompt. Tell the agent: 'Show my heart rate trends from October 1st to October 31st.' Use the date range capabilities of tools like get_heart_timeseries.
Ignoring data source limitations
Assuming the agent can track my weight using get_body_weight data alongside my calorie intake from get_foods_date, even if the data was logged on different devices.
→
Always verify the data source and time correlation. Check the get_devices tool first to ensure all necessary data streams are syncing correctly before starting a major analysis.
When It Fits, When It Doesn't
Use this server if your goal is deep, longitudinal analysis of physiological metrics. You need to correlate things like sleep quality (get_sleep_timeseries) with physical output (get_activities_timeseries) or metabolic function (get_foods_date). The data must be time-series based and cover diverse metrics (heart rate, SpO2, weight).
Don't use this if you just need to view a single metric (like checking your steps for today). Use a simple fitness tracker app instead. If you need to combine multiple data types—for instance, seeing how low SpO2 correlates with poor sleep—this is the right tool. If you just want to see what your steps were yesterday, it's overkill.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Fitbit. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 14 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Figuring out how your activity level impacts your sleep is a pain.
Right now, you have to open the Fitbit app. You check your sleep score for last night. Then you open another tab or screen to check your step count for the same day. You copy the sleep score, you copy the steps, and then you open a third place to manually plot them. It's clicking through three separate dashboards just to answer a simple 'how did I feel?' question.
With this MCP server, you ask your agent: 'Compare my sleep score to my steps over the last week.' Your agent runs `get_sleep_timeseries` and `get_activities_timeseries`, then delivers the correlation directly in the chat. You get the answer, not a jumble of graphs.
Fitbit MCP Server: See your full health metrics in one conversation.
You no longer need to switch between the dedicated sections for heart rate, nutrition, and activity. The agent pulls `get_heart_date` for resting heart rate and `get_foods_date` for your meals, then summarizes the relationship. It's all one workflow.
The difference is that you stop collecting data points and start asking causal questions. Your agent correlates the numbers for you.
Common Questions About Fitbit MCP
How do I check my sleep trends using get_sleep_timeseries? +
Use get_sleep_timeseries and provide a start and end date (YYYY-MM-DD). This tool gives you daily summaries, including sleep efficiency and the breakdown of sleep stages, across a full date range.
Can I compare my heart rate data with my activity data? +
Yes. Your agent can run get_heart_timeseries and get_activities_timeseries in sequence. This allows you to see how your resting heart rate changes over time relative to your physical activity levels.
What is the best tool for checking weight changes? +
Use get_body_weight for a single date, or get_activities_timeseries if you want weight trends over a period (though get_body_weight is the primary source). The tool returns weight in kg, BMI, and fat percentage.
How do I get my blood oxygen saturation (SpO2) data? +
Call get_spo2 and provide the specific date. This tool returns the average SpO2 percentage and the minimum and maximum values recorded on that day.
How do I check my food intake for a specific day using get_foods_date? +
The get_foods_date tool returns total calories, macros (carbs, protein, fat), water intake, and a list of logged foods for that day. You can use this to quickly see your nutritional summary and track dietary adherence.
How can I see my total activity data over a long period with get_activities_timeseries? +
The get_activities_timeseries tool gets activity metrics like steps, distance, and calories over periods ranging from 1 day up to 1 year. You can specify the date range and detail level to analyze trends.
What is the process for setting up the Fitbit connection? +
You must first subscribe to the server and generate an OAuth2 access token from your Fitbit Developer Portal. This token allows your AI client to access your health data securely.
Does the server support retrieving data from multiple connected devices using get_devices? +
Yes, the get_devices tool returns details for all Fitbit devices linked to your account. This includes version, MAC address, battery level, and last sync time, letting you manage your connected hardware.
Can I query sleep data for a specific date range? +
Yes! Use the sleep time series tool to query sleep trends across any date range. You can also inspect a single night in detail with the sleep date tool, including all sleep stages.
What health metrics can I access? +
You can access 14 different health metrics: activities, sleep (date & time series), heart rate (date & time series), SpO2, breathing rate, cardio fitness score, body weight, water intake, food logs, device info, and user profile.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
TransportAPI Alternative
UK public transport intelligence — live departures, journey planning, train fares, timetables, and postcode-based station search via AI.
BTC.com API (BTC.com Explorer & Pool API)
Access real-time Bitcoin blockchain data and mining pool statistics including blocks, transactions, addresses, and worker performance.
HealthData.gov (HHS Open Data)
Access and query thousands of U.S. health datasets from HHS — browse the catalog and perform deep data analysis via SoQL.
You might also like
Dotdigital
Equip your AI agent to manage email campaigns, track contacts, and monitor marketing automation via the Dotdigital API.
AbstractAPI
Equip your AI agent with AbstractAPI's data enrichment — validate emails, geolocate IPs, check phone numbers, and enrich company data.
BallDontLie
NBA data platform — access player stats, team info, and game results via AI.