Skip to main content
Glama
Sign In
Quantified Self MCP Server

Quantified Self MCP Server

by Thecimal
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to Quantified Self MCP Server

  • google-health-mcp

    partymola
    A
    license
    A
    quality
    B
    maintenance
    MCP server for the Google Health API: heart rate, activity, sleep, SpO2, HRV, ECG and irregular-rhythm notifications, read into a local SQLite cache for fast offline queries and trend analysis. OAuth 2.0 with automatic token refresh, incremental sync, a cache-only offline mode, and a doctor command that diagnoses a setup without spending quota.
    24
    417 PyPI
    1
    GPL 3.0

Related Servers

  • finanzas-pyme

    JuanDsm04
    F
    license
    A
    quality
    B
    maintenance
    Enables LLMs to answer small business finance questions about spending, sales trends, cash flow projections, and profitability using a local SQLite database.
    6
    -

  • garmin-mcp

    VictorVel8
    A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI agents to query a local SQLite export of Garmin Connect data — daily summaries, sleep stages, HRV, readiness, activities and intraday heart rate, stress, Body Battery and SpO2 — through tools like get_day, compare_periods, get_sleep_detail, get_timeseries and a read-only run_sql. This lets an agent compare periods against personal baselines while keeping raw payloads, credentials and network ports out of reach.
    MIT

  • mydata

    bibekg
    A
    license
    Not graded
    quality
    D
    maintenance
    Enables querying personal data synced from services like Lunch Money and Strava using SQL via Claude.
    11 npm
    1
    MIT

  • mcp-sqlite-tools-plus

    MauricioPerera
    A
    license
    B
    quality
    D
    maintenance
    Enables AI agents to interact with local SQLite databases with full CRUD, schema introspection, foreign key relations, generated columns, and multi-format import/export (CSV, JSON, XLSX) through natural language.
    26
    14 npm
    MIT
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.2/5.0

Scored across 20 tools

Disambiguation4/5

Nearly every tool carries explicit 'Use this tool when / Do not use this tool when' routing rules, so an agent can separate logging (daily vs. measurement vs. workout) and the analytics family (baseline/trend/anomaly/correlation/compare/recent-changes/explain) reliably. The remaining friction is in the raw-row readers — read_measurements, get_metric_provenance and aggregate_measurements all surface per-source day-level data and their boundary is only implied by prose, not by name.

Naming Consistency5/5

All 20 names are snake_case verb_noun pairs with a stable verb vocabulary: log_/clear_ for writes, read_/get_ for reads, and detect_/find_/calculate_/compare_/explain_/aggregate_ for analysis. No camelCase, no bare nouns, and the prefix reliably predicts whether a tool mutates data.

Tool Count4/5

Twenty tools is at the heavy end of the range, but they divide into coherent groups (4 writes, 4 raw readers, 7 analytics, 3 status/export) and each covers an operation the others do not. A couple of the deeper analytics tools (explain_metric_change, get_recent_changes) could arguably be compositions of simpler ones, which keeps this just shy of a 5.

Completeness4/5

The surface is strong: logging, correction via clear_metric, aggregate and raw reads, CSV export, freshness/import status, and a full analytics ladder from baseline through correlation to a why-bundle. Gaps remain in lifecycle coverage — there is no way to edit or delete an individual measurement row or a workout session (only clear_metric at day granularity), and imports can be inspected but not triggered.

Maintenance

ActivityActive
ResponsivenessLimited data

Resources