FitBit MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FITBIT_ACCESS_TOKEN | Yes | Your Fitbit access token obtained through OAuth 2.0 authorization flow |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 16 tools
Each tool has a clearly distinct purpose targeting specific Fitbit data categories like heart rate, sleep, steps, badges, etc. There is no overlap or ambiguity between tools - an agent can easily select the right tool for each type of data retrieval.
All 16 tools follow a perfectly consistent 'getNoun' or 'getAdjectiveNoun' naming pattern using camelCase. The naming convention is uniform throughout the entire toolset with no deviations.
16 tools is slightly high but reasonable for a comprehensive fitness data API. Each tool represents a distinct data category that Fitbit tracks, so most tools earn their place, though some consolidation might be possible.
The toolset is severely incomplete as it only provides read-only data retrieval operations. There are no tools for creating, updating, or deleting any Fitbit data (like logging food/water, starting activities, or updating goals), which are essential for a full fitness tracking workflow.