Skip to main content
Glama
Sign In
rudeayelo

aimharder-mcp

by rudeayelo
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Related Servers

Alternatives to aimharder-mcp

No user-submitted related servers found.

    Related Servers

    • openGym MCP Bridge

      Nirvana-Z777
      A
      license
      B
      quality
      A
      maintenance
      Enables MCP clients to read account status, plans, and recent workouts, search official exercise names, and, when writes are enabled, apply confirmed preview-first plan changes and historical workout logs.
      22
      MIT

    • fitness-mcp

      wbratz
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables conversational logging and retrieval of workouts, sets, weigh-ins, meals, goals, plans, and progress photos through MCP-capable AI clients, with authenticated per-user storage and export/query capabilities.
      ISC

    • set-and-signal

      aranlucas
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables MCP clients to connect to a privacy-first, self-hostable workout planning and training log, allowing coaching agents to preview and apply program changes while accessing training data through OAuth-protected endpoints.
      AGPL 3.0

    • garmin-mcp

      Sinfjell
      A
      license
      Not graded
      quality
      B
      maintenance
      Connects MCP clients to Garmin Connect data, enabling queries about activities, sleep, heart rate, body battery, and training status.
      2
      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 18 tools

    Disambiguation4/5

    The prepare/execute pairing is a deliberate two-phase safety pattern, and the descriptions sharply delineate each pair (booking creation, cancellation, late cancellation, activity publication, deletion). The only soft overlaps are among the read tools — get_class_sessions vs get_published_workouts (schedule vs workout content) and find_exercise_1rm vs get_exercise_1rm vs get_exercise_rm_progression (search vs latest value vs series) — but descriptions make the boundaries clear enough that misselection is unlikely.

    Naming Consistency5/5

    All 18 names use snake_case with a predictable verb_noun shape (get_*, find_*, prepare_*, execute_*). The prepare/execute prefixes map one-to-one onto the same noun phrases, so an agent can infer the partner tool from any name. execute_late_booking_cancellation is a consistent extension of execute_booking_cancellation rather than a deviation.

    Tool Count4/5

    18 tools sits slightly above the comfortable band, but the count is largely explained by the mandatory prepare/execute split on five mutating actions plus one late-cancellation escalation path. Every tool maps to a distinct step in a real workflow, so the surface is dense rather than padded.

    Completeness3/5

    Read coverage is strong (schedule, upcoming/history bookings, personal activity, published workouts, 1RM and progression, account context) and the booking lifecycle is fully covered including late cancellation. However, published activities can be created and deleted but never edited, and waitlisted state is reported without any tool to join or leave a waitlist; there is also no way to query credit/balance despite cancellation warnings referencing credit loss.

    Maintenance

    ActivityActive
    ResponsivenessResponsive

    Resources