FitbitSAFE
Give your AI assistant access to your Fitbit data for personalized health insights, trend analysis, and automated tracking. Works with Claude Desktop and other MCP-compatible AI tools.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://dev.fitbit.com/) [](https://github.com/TheDigitalNinja/mcp-fitbit/actions/workflows/ci.yml) [](https://coveralls.io/github/TheDigitalNinja/mcp-fitbit?branch=main) [](https://opensource.org/licenses/MIT) [](https://badge.fury.io/js/mcp-fitbit) [](https://www.npmjs.com/package/mcp-fitbit)
Connect AI assistants to your Fitbit health data
Give your AI assistant access to your Fitbit data for personalized health insights, trend analysis, and automated tracking. Works with Claude Desktop and other MCP-compatible AI tools.
What it does
🏃 Exercise & Activities - Get detailed workout logs and activity data 😴 Sleep Analysis - Retrieve sleep patterns and quality metrics ⚖️ Weight Tracking - Access weight trends over time ❤️ Heart Rate Data - Monitor heart rate patterns and zones 🍎 Nutrition Logs - Review food intake, calories, and macros 👤 Profile Info - Access basic Fitbit profile details
Ask your AI things like: "Show me my sleep patterns this week" or "What's my average heart rate during workouts?"
Quick Start
🚀 Want to test the tools right away?
Option 1: Install from npm (Recommended)
- Get Fitbit API credentials
- Create an app with OAuth 2.0 Application Type:
Personal - Set Callback URL:
http://localhost:3000/callback - Note your Client ID and Client Secret
- Install the package globally:
npm install -g mcp-fitbit
- Add to your Claude Desktop config file:
b2309ec0f5afOBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-fitbit --env FITBIT_CLIENT_SECRET=${FITBIT_CLIENT_SECRET} -- npx -y [email protected]{
"mcpServers": {
"mcp-fitbit": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"FITBIT_CLIENT_SECRET": "${FITBIT_CLIENT_SECRET}"
}
}
}
}Exposed tools (9)
9 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
get_activity_goals | read | Get the raw JSON response for user |
get_activity_timeseries | read | Get the raw JSON response for activity time series data from Fitbit over a date range (max 30 days). Supports various resource paths like |
get_azm_timeseries | read | Get the raw JSON response for Active Zone Minutes (AZM) time series data from Fitbit over a date range (max 1095 days). Returns total AZM plus breakdown by fat burn, cardio, and peak zones. |
get_daily_activity_summary | read | Get the raw JSON response for daily activity summary from Fitbit for a specific date. Includes goals, steps, calories, distances, and heart rate zones. Requires a |
get_exercises | read | Get the raw JSON response for exercise and activity logs from Fitbit after a specific date. Requires |
get_profile | read | Get the raw JSON response for the user |
get_sleep_by_date_range | read | Get the raw JSON response for sleep logs from Fitbit for a specific date range. Requires |
get_weight | read | Get the raw JSON response for weight entries from Fitbit for a specified period ending today. Requires a |
test_tool | read | A test tool |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (1)
@modelcontextprotocol/sdk, @types/express, dotenv, express, open, simple-oauth2, zod, @eslint/js
Gates applied: no_behavioural_pass.
b2309ec0f5affull audit observations/trust-audit/mcp-server/thedigitalninja__fitbit.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | b2309ec0f5af | SAFE | B | 89 | first audit |
Questions
What is the Fitbit MCP server?
Give your AI assistant access to your Fitbit data for personalized health insights, trend analysis, and automated tracking. Works with Claude Desktop and other MCP-compatible AI tools.
What tools does Fitbit expose?
9 in total: 9 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Fitbit safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Fitbit need?
It reads FITBIT_CLIENT_SECRET from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Fitbit run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as mcp-fitbit at 1.0.1.
How current is this page?
The grade is for one exact copy of the source (b2309ec0f5af), read on 2026-10-08. The repository is watched and re-audited when it changes.