Skip to main content
Glama
cunicopia-dev

whoop-postgres-mcp

by cunicopia-dev
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Related Servers

Alternatives to whoop-postgres-mcp

No user-submitted related servers found.

    Related Servers

    • whoop-ai-mcp

      nMoreau39122
      F
      license
      Not graded
      quality
      A
      maintenance
      Enables AI assistants to query a user's WHOOP recovery, sleep, HRV, strain, workouts and body measurements through 16 read-only tools, including today's status, personal baselines, sleep debt, trends and period comparisons. Runs locally, requires no data exports, and supports aggregate mode that limits responses to high-level summaries.
      4 npm
      -

    • garmin-givemydata

      nrvim
      A
      license
      B
      quality
      A
      maintenance
      Downloads all your Garmin health and fitness data into a local SQLite database and exposes 45 MCP tools for AI analysis, enabling assistants to query sleep, training load, HRV, and more.
      48
      129 PyPI
      164
      AGPL 3.0

    • whoop-ai-mcp

      lukas61043
      F
      license
      Not graded
      quality
      A
      maintenance
      Enables AI assistants to read a user's WHOOP recovery, sleep, HRV, strain, and workout history through a local, read-only server with tools for today's status, personal baselines, sleep debt, trends, and period comparisons. It supports Claude Desktop, Claude Code, Codex, and GitHub Copilot, letting users ask natural-language questions about their health data without exporting it themselves.
      4 npm
      -

    • health-mcp

      danielv27
      F
      license
      A
      quality
      B
      maintenance
      Provides a unified MCP interface to a personal health database, enabling AI agents to sync lifting workouts from Hevy, log food intake against a catalog, and run read-only SQL queries to cross-reference training and nutrition data.
      6
      1
      -
    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

    A4.1/5.0

    Scored across 10 tools

    Disambiguation4/5

    Each tool targets a distinct data type (recovery, sleep, workouts, cycles) or action (auth, connect, sync, status), so boundaries are mostly clear. whoop_overview aggregates recovery/sleep/workouts/strain and thus overlaps with the individual read tools and whoop_baseline, but its 'one-call snapshot' description mostly disambiguates it.

    Naming Consistency5/5

    Every tool uses the same whoop_<noun> snake_case prefix with no mixing of conventions. The pattern is predictable and readable throughout.

    Tool Count5/5

    Ten tools is a well-scoped set: two auth tools, one sync, one status, one baseline, and six read tools. Each earns its place with no obvious redundancy.

    Completeness4/5

    The surface covers the full lifecycle: OAuth connect, sync, sync health, and reads across recovery, sleep, workouts, cycles, baseline, and overview. Minor gaps like token revocation/disconnect or delete operations are absent but not blocking for the read-oriented purpose.

    Maintenance

    ActivitySlowing
    ResponsivenessNo issues

    Resources