Skip to main content
Glama
Zsadigzade

Trainbud

by Zsadigzade
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Related Servers

Alternatives to Trainbud

Related Servers

  • Garmin MCP

    davidmosiah
    A
    license
    B
    quality
    A
    maintenance
    Local-first MCP server that connects AI agents to your Garmin sleep, HRV, Body Battery, stress, training readiness and activities, keeping tokens on your machine.
    42
    262 npm
    12
    MIT

  • garmin-mcp

    aayush-lunawat
    A
    license
    Not graded
    quality
    C
    maintenance
    A local MCP server that exposes your Garmin Connect data—sleep, HRV, training readiness, workouts, and more—to any MCP-compatible AI assistant. Runs entirely on your machine and keeps your Garmin credentials private.
    MIT

  • Garmin Open MCP

    limited
    A
    license
    A
    quality
    B
    maintenance
    Unofficial MCP server bridging Garmin Connect to MCP clients and ChatGPT, providing tools to access health data, activities, and trends via a self-hosted API.
    11
    MIT

  • Garmin Connect MCP Server

    DankeyDevDave
    A
    license
    Not graded
    quality
    C
    maintenance
    Connects Garmin Connect data to MCP-compatible clients, providing access to fitness activities, health metrics, and training plans. It supports advanced features like headless 2FA and automated MFA retrieval to enable seamless health data interaction through natural language.
    1
    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

A3.6/5.0

Scored across 15 tools

Disambiguation4/5

Most tools are clearly distinct, but some overlap exists between get_findings, get_recovery_status, get_training_insights, and get_week_review, which all return aggregated health/training metrics. Descriptions help clarify their specific focuses (anomalies vs. recovery score vs. weekly summary vs. week-over-week comparison), and get_latest_activity vs get_activities_range are distinct by scope. Overall, an agent can likely select the right tool with careful reading.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern in snake_case: most start with 'get_' for retrieval, with a few action verbs (remember_context, compare_workouts, log_subjective) that are equally clear. No mixed conventions or vague names—every name is self-explanatory.

Tool Count5/5

15 tools is at the upper end of the ideal range but well-scoped for a training assistant that combines user context, Garmin metrics, and comparative analysis. Each tool covers a distinct need, from retrieving raw data to high-level insights, without redundancy or bloat.

Completeness4/5

The surface covers the core lifecycle: user context (remember/get), subjective logging, comparisons, and a wide array of metric getters (sleep, HR, recovery, body comp, stress, VO2, activities). Minor gaps exist—no direct update/delete for context, and some overlapping insights—but these are not critical for the server's purpose and agents can work around them.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources