Skip to main content
Glama
turnnoblindeye

Wellness Project MCP

by turnnoblindeye
OverviewSchemaSourceRelated ServersDiscussions(1)Admin
Python
Remote

Related Servers

Alternatives to Wellness Project MCP

  • google-health-mcp

    partymola
    A
    license
    A
    quality
    A
    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.
    19
    67 PyPI
    GPL 3.0

Related Servers

  • health-mcp

    almostjacked
    A
    license
    Not graded
    quality
    A
    maintenance
    An MCP server that securely syncs and queries your health data from Apple Health, storing it in your own Supabase Postgres database and exposing tools for AI assistants to retrieve weight, calories, macros, and more.
    14 npm
    MIT

  • Almanac MCP Server

    corcoran
    A
    license
    Not graded
    quality
    B
    maintenance
    Self-hosted fitness tracking MCP server that gives AI assistants access to your nutrition, training, weight, sleep, and accomplishment data via 77 tools and 5 resources. Enables natural-language logging and querying of personal health metrics through Claude or ChatGPT.
    1
    BSD 2-Clause "Simplified"

  • Health Export AI

    PhilipAD
    A
    license
    A
    quality
    A
    maintenance
    An MCP server that enables AI agents to query Apple Health data (190+ metrics) in natural language, including trends, comparisons, and structured exports.
    14
    77 npm
    4
    MIT

  • whoop-mcp

    Saadh05
    F
    license
    Not graded
    quality
    D
    maintenance
    MCP server that connects Whoop fitness data to Claude, enabling natural language queries about recovery, sleep, workouts, and more.
    -

  • google-health-mcp-server

    madfreakz
    A
    license
    A
    quality
    D
    maintenance
    MCP server to read daily activity, sleep, heart rate, and body metrics from Google Health API, allowing AI assistants like Claude to access your health data. Optionally syncs health metrics to an Obsidian vault.
    5
    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

A3.9/5.0

Scored across 73 tools

Disambiguation3/5

Most tools are organized by clear domain and CRUD pairs, but there is substantial overlap between the 15+ show_* visualization tools and the list_/get_ data tools (e.g., show_meal_diary vs list_meals, show_workout vs get_workout, show_week_sleep vs list_sleep). Additionally, log_meal and mark_empty_day can both create a 'Fast day' entry, creating a real boundary ambiguity. The long descriptions help, but an agent will frequently need to choose between presentational and data-retrieval variants of the same underlying query.

Naming Consistency4/5

The set mostly follows a consistent log_/list_/get_/update_/delete_/show_ verb-noun pattern, which makes domains easy to recognize. Deviations exist: manage_supplement and manage_recovery_strategy bundle multiple actions under a vague verb, create_goal appears without a matching create_* family, and add_or_update_personal_context breaks the convention. Overall the naming is predictable and readable despite a few exceptions.

Tool Count1/5

73 tools is far beyond the 15-25 range where a single server starts to feel heavy, and it exceeds the 50+ extreme mismatch threshold. The server bundles a dozen-plus domains into one namespace, dramatically increasing selection difficulty for agents. This would be much better factored into domain-specific servers or a smaller set of more polymorphic tools.

Completeness3/5

Most domains have solid CRUD/lifecycle coverage: meals, workouts, labs, injuries, wellbeing, recovery sessions, and cycles all support create/read/update/delete. However, there are notable gaps: runs have no update tool (only log/list/delete), sleep/body-metrics/wearable entries have no delete path, and personal context explicitly has no delete capability. These create dead ends for common correction workflows, even though several can be partially worked around via upserts.

Maintenance

ActivityMaintained
ResponsivenessSlow

Resources