pickfit

BrowseMCP servers

Quantified Self MCP

Local MCP server giving AI agents structured access to personal health history.

Tested on Linux

Use it

Linux x86_64

  1. install quantified-self-mcp via uv tool install

    uv tool install quantified-self-mcp

Check that it works

quantified-self-doctor --help; quantified-self-doctor

The 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.csv
quantified-self-init-db /tmp/health_sample.csv --report

Add it to your agent

claude mcp add quantified-self-mcp -- quantified-self-mcp
JSON 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 data
    How to use it
    1. Import a CSV of daily health data with quantified-self-init-db <file> --report.
    2. Add quantified-self-mcp as a server in your MCP client.
    3. Ask your agent to call read_health_data with a start and end date.
    Tested
  • Analyze your health history over time
    How to use it
    1. Import your data with quantified-self-init-db <file> --report.
    2. Connect quantified-self-mcp to your MCP client.
    3. Ask your agent to call calculate_metric_trend with a metric (such as steps) and a date range.
    Tested
  • Import your existing health history
    How to use it
    1. Run quantified-self-init-db <file> --report on a CSV with a date column and one column per metric.
    2. Connect quantified-self-mcp to your MCP client and call get_import_status to check the import.
    Tested
  • Trace results back to the source data
    How to use it
    1. Import your data with quantified-self-init-db <file> --report.
    2. Connect quantified-self-mcp to your MCP client.
    3. Call get_metric_provenance with a metric and a date to see where the value came from.
    Tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Connects
  3. 4 of 4 features work
  4. 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

How to read a tool card

Stitching
pickfit installed this tool itself. Everything under the stitches comes from that run. A tool pickfit has not run never gets stitches.
Verified on your OS
The install steps ran on the system you chose. “Ran on Linux only” means it has not been run on yours yet.
macOS, Linux and WindowsWhere it ran
Green OS marks: pickfit ran the install steps there. Grey ones: the README says it runs there, and pickfit has not tried.
How far the run got
Installs and starts, its main function works, its service answers, it produces model output. A window means a desktop app opened; a plug, an MCP client used it. The mark sits beside the run’s result, under “Why it fits and how we know” and in “How pickfit tested it”.
Visual check
pickfit looked at screenshots of the app. Green: it looks right. Amber with a number: things that look wrong; open it to see them. Grey and dashed: not checked yet.
Known vulnerabilities
Known high or critical vulnerabilities (OSV.dev) in what it installs. Green: none known. Red with a number: how many; open it for the list, and read it before you install. Grey and dashed: not checked, which does not mean safe.
About the run
The day it ran, and the version that ran.
Source of a reason
Every reason a pick fits rests on one profile field. Open the reason to see the field and the value it relies on.
Hidden gem
High quality, little known.
Quality and popularity
Two scores out of 100. Quality: how well it installed and worked when pickfit tried it, and how good its install docs and upkeep are. Popularity: from stars, downloads and Hacker News.
Features checked
Of the main features the README advertises, how many the run actually exercised (green), and how many failed (red). Grey ones were not checked, and the card says why.
Not verified
A well-known tool Fitz mentions from general knowledge. No run record, no steps, no score.