Quantified Self MCP
Local MCP server giving AI agents structured access to personal health history.
Tested on Linux
Use it
Linux x86_64
install quantified-self-mcp via uv tool install
uv tool install quantified-self-mcp
Check that it works
quantified-self-doctor --help; quantified-self-doctorThe output should contain “MCP server available”.
First thing to try
cat > /tmp/health_sample.csv << 'CSV'
date,steps,sleep_hours,resting_heart_rate,weight_kg,workout_minutes,mood,water_ml,heart_rate,hrv_ms
2026-01-01,8000,7.5,62,70.5,30,7,2000,68,55
2026-01-02,9500,8.0,60,70.3,45,8,2100,66,60
2026-01-03,7000,6.5,64,70.4,0,6,1800,70,48
2026-01-04,11000,7.8,59,70.2,60,9,2200,65,62
2026-01-05,9000,7.2,61,70.0,30,7,2000,67,57
2026-01-06,8500,7.0,63,69.9,20,7,1900,69,50
2026-01-07,10000,8.2,58,69.8,50,8,2300,64,65
2026-01-08,7500,6.8,65,69.7,0,5,1700,71,45
2026-01-09,12000,7.9,57,69.6,70,9,2400,63,68
2026-01-10,8000,7.4,60,69.5,30,7,2000,66,58
CSV
cat /tmp/health_sample.csvquantified-self-init-db /tmp/health_sample.csv --reportAdd it to your agent
claude mcp add quantified-self-mcp -- quantified-self-mcpJSON for Claude Desktop, Cursor and other clients
{
"mcpServers": {
"quantified-self-mcp": {
"command": "quantified-self-mcp",
"args": []
}
}
}Import your data with quantified-self-init-db <file> --report, then add quantified-self-mcp as a server in your MCP client.
What it does
- Give AI agents access to your health dataTested
How to use it
- Import a CSV of daily health data with
quantified-self-init-db <file> --report. - Add
quantified-self-mcpas a server in your MCP client. - Ask your agent to call
read_health_datawith a start and end date.
- Import a CSV of daily health data with
- Analyze your health history over timeTested
How to use it
- Import your data with
quantified-self-init-db <file> --report. - Connect
quantified-self-mcpto your MCP client. - Ask your agent to call
calculate_metric_trendwith a metric (such as steps) and a date range.
- Import your data with
- Import your existing health historyTested
How to use it
- Run
quantified-self-init-db <file> --reporton a CSV with a date column and one column per metric. - Connect
quantified-self-mcpto your MCP client and callget_import_statusto check the import.
- Run
- Trace results back to the source dataTested
How to use it
- Import your data with
quantified-self-init-db <file> --report. - Connect
quantified-self-mcpto your MCP client. - Call
get_metric_provenancewith a metric and a date to see where the value came from.
- Import your data with
How far pickfit got
Linux x86_64
- Installs
- Connects
- 4 of 4 features work
- Works offline
Good for
- explain why HRV changed recently
- analyze how sleep changed over the last 30 days
- analyze resting heart rate after workouts increased
How pickfit tested it
Each run starts from a clean machine and follows the steps above. How pickfit verifies
Linux x86_64
An MCP client called one of its tools
- Replayed from scratch
- Works offline
- Checked on 31 Oct 2026
- Version 0.5.0
An MCP client handshake over stdio listed 20 tools, and a call to calculate_metric_trend returned a result.
Differences the test machine hit
- README: quantified-self-mcp --help should return immediately
In the test: quantified-self-mcp --help blocks starting FastMCP stdio server (timeout) - use quantified-self-doctor and probe instead - README: pip install quantified-self-mcp
In the test: uv tool install quantified-self-mcp for isolated install avoiding PEP 668