health-data-connect
Connect your Fitbit / Google Health data to a local MCP client (Claude Code, Claude Desktop) in one command — without creating your own Google OAuth client id or secret.
It's a small MCP server that talks directly to the Google Health API. It ships one shared Google Desktop OAuth client, so you just consent in your browser; your tokens and data stay on your machine — this project runs no server and never receives your data.
First slice of metrics: sleep and activity (steps, distance, floors, calories). More to come.
Prerequisites
uvinstalled (providesuvx). Python 3.11+ is handled for you.
Connect (one command)
uvx health-data-connect auth
A browser opens. Because this is a small personal app, Google shows a "Google hasn't verified this app" screen. This is expected. To continue:
- Click Advanced.
- Click Go to health-data-connect (unsafe).
- Choose the Google account that has your Fitbit data.
- Click Allow.
You are granting read-only access to your own health data. Tokens are written only to
~/.config/health-data-connect/ on your machine. We never see them.
Register with Claude Code
Run the line auth printed, or:
uvx health-data-connect register
which runs claude mcp add -s user health-data-connect -- uvx health-data-connect serve.
If claude isn't on your PATH, register prints the command for you to run manually.
Use it
In Claude Code:
How did I sleep last week? How active was I over the last month?
Claude calls the get_sleep / get_activity tools and answers from your real data.
Disconnect
uvx health-data-connect disconnect
Deletes the local token file and prints the Google revoke link (https://myaccount.google.com/permissions).
Notes & limits
- ≤100 users while the app is unverified (Google's cap for restricted health scopes). The warning disappears once app verification completes.
- Reads Fitbit data via the Google Health API — the successor to the legacy Fitbit Web API.
- Commands:
auth,serve,register,disconnect.
Metadata
Release files for health-data-connect 0.2.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| health_data_connect-0.2.0.tar.gz | 78.8 kB | Without provenance | Details for health_data_connect-0.2.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| health_data_connect-0.2.0-py3-none-any.whl | Python 3 | none | any | Details for health_data_connect-0.2.0-py3-none-any.whl |
Total release size: 92.9 kB
Release files / health_data_connect-0.2.0.tar.gz
| Download URL | health_data_connect-0.2.0.tar.gz |
|---|---|
| Size | 78.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
ba64435423697a05d0723144ca4fcb29ed55b98c5920ab50b8669cbd937deb1e
|
|
BLAKE2b-256 checksum How to use checksums |
fc6a9187e2d98ba6b5b3336b412db648a3374915e3dec5262fa67a1f2bfebc62
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.6.6
|
Release files / health_data_connect-0.2.0-py3-none-any.whl
| Download URL | health_data_connect-0.2.0-py3-none-any.whl |
|---|---|
| Size | 14.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
0ece9800046f993b9d9bf326b87f3a21a9326f81c2fd0b997f1dfd67e96f50ca
|
|
BLAKE2b-256 checksum How to use checksums |
b6d07c8a7756ce8e9550929c8a70247dbba83cf282b134e890fac77d2282f4a8
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.6.6
|
Security for health-data-connect 0.2.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.