Privacy-first, unofficial Fitbit MCP server for AI health, sleep, activity and heart-rate agents.
Privacy-first, unofficial Fitbit MCP server for AI health, sleep, activity and heart-rate agents.
http://127.0.0.1:3000/callback - Intraday heart-rate access requires the Fitbit app to be approved for intraday data (varies per app)Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| fitbit_connection_status | verify local setup before calling Fitbit |
| fitbit_data_inventory | inventory supported data domains, scopes, privacy modes and recommended first calls without calling Fitbit APIs. |
| fitbit_daily_summary | readiness, activity, sleep and heart context for today |
| fitbit_weekly_summary | scorecard, comparison vs prior week, next-week plan |
{
"mcpServers": {
"fitbit": {
"command": "npx",
"args": ["-y", "fitbit-mcp-unofficial"]
}
}
}Configuration as documented by the project. Restart the client after saving.
http://127.0.0.1:3000/callback - Intraday heart-rate access requires the Fitbit app to be approved for intraday data (varies per app)| Variable | Description | Required |
|---|---|---|
| FITBIT_CLIENT_ID | Configuration value read at startup. | Optional |
| FITBIT_CLIENT_SECRET | Credential the server authenticates with. | Yes |
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
Agent Interviews is an AI-powered research platform designed to conduct qualitative interviews an...
Generate documents, process PDFs, and manage e-signature workflows using the PDFGate API.
Bridge Claude with Google's Antigravity CLI (agy) for code review and second opinions
eBPF-based GPU causal observability with 7 MCP tools for AI-assisted GPU debugging