How to Use the Fitbit MCP in Mastra AI

Q: How do I add Fitbit tools to a Mastra AI agent?

You initialize the MCPClient with the server URL and call mcpClient.listTools(). Then, you spread those tools directly into your Mastra agent configuration. This gives your agent instant access to endpoints like getactivitiesdate and getprofile.

Q: How do I require human approval before a Mastra AI agent logs Fitbit water intake?

You set the requireToolApproval flag on the getwater tool inside your Mastra agent. When the agent attempts to log water volume, the workflow pauses until you manually approve the action. This prevents incorrect logs from messing up your database.

Build automated health coaching workflows with Mastra AI and live Fitbit metrics.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fitbit MCP to Mastra AI

Create your Vinkius account to connect Fitbit to Mastra AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Fitbit with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build automated activity and weight workflows in Mastra AI

This Fitbit MCP Server exposes `get_activities_date` and `get_body_weight` as executable tools for your Mastra agents. You can build a workflow that checks a user's step count, calculates their calorie burn, and triggers a conditional branch if they miss their daily movement target. Mastra AI runs these checks on a cron schedule, automatically retrying the API call with exponential backoff if the network hiccups. Your agent handles the raw weight and step metrics without you writing custom error-handling loops.

Trigger coaching alerts based on sleep quality

This Fitbit MCP Server delivers deep sleep metrics using `get_sleep_date` and `get_sleep_timeseries` to your Mastra workflows. If the retrieved efficiency score drops below seventy percent, your agent can route that data to a notification step. You configure human-in-the-loop validation using `requireToolApproval` before sending any automated advice. This ensures a human coach reviews the sleep stages and REM duration before the agent messages the user.

Track cardiovascular fitness trends automatically

This Fitbit MCP Server provides VO2 Max and resting heart rate data via `get_cardio_fitness_score` and `get_heart_timeseries`. Your Mastra AI client pulls these trends weekly to evaluate physical conditioning. You deploy the entire monitoring loop to your cloud with a single command. The client auto-detects the transport protocol, letting your agents query cardio metrics without manual configuration.

Setup guide

Set up Fitbit MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Fitbit tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "fitbit-mcp-client",
  servers: {
    "fitbit-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Fitbit Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Fitbit tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Fitbit transactions"
);
console.log(result.text);

Get your connection token →

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.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Fitbit now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Fitbit MCP in Mastra AI

You initialize the `MCPClient` with the server URL and call `mcpClient.listTools()`. Then, you spread those tools directly into your Mastra agent configuration. This gives your agent instant access to endpoints like `get_activities_date` and `get_profile`.

Yes, Mastra's workflow engine uses automatic retries with exponential backoff. If a call to `get_heart_date` or `get_sleep_date` hits an API rate limit, the client pauses and retries. This keeps your health-tracking workflows running without crashing.

You set the `requireToolApproval` flag on the `get_water` tool inside your Mastra agent. When the agent attempts to log water volume, the workflow pauses until you manually approve the action. This prevents incorrect logs from messing up your database.

Yes, the Mastra client auto-detects both Streamable HTTP and SSE transports. It establishes a stable connection to the server, letting your agents pull biometric updates the moment they sync.

Your steps, active minutes, and calorie logs are sent directly to the agent over an encrypted connection. The server operates in an ephemeral V8 sandbox, meaning your raw metrics are never cached or saved. Your data remains fully under your control.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript