Skip to main content
Glama
davidmosiah

Strava MCP

by davidmosiah
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Related Servers

Alternatives to Strava MCP

No user-submitted related servers found.

    Related Servers

    • catence

      rifusaki
      A
      license
      B
      quality
      A
      maintenance
      MCP server for local fitness-data extraction and analysis from Garmin Connect, Intervals.icu, and Strava. Provides read-only analytical tools over DuckDB and targeted Strava enrichment.
      35
      27 npm
      AGPL 3.0

    • garmin-mcp

      knahsirV
      F
      license
      Not graded
      quality
      B
      maintenance
      Privacy-focused Garmin Connect MCP server for triathlon training, enabling analysis of health metrics, activities, training load, and structured workout creation.
      -

    • Strava MCP

      ljcl
      A
      license
      Not graded
      quality
      A
      maintenance
      An MCP server that supplements the official Strava connector with write access, segments, routes, photos, derived analysis, and interactive visualizations.
      11 npm
      MIT

    • strava-mcp

      EthanDM
      A
      license
      A
      quality
      C
      maintenance
      A read-only local MCP server for querying your own Strava data from Codex, providing tools for activities, athlete profile, stats, gear, and more.
      16
      11 npm
      MIT

    • fitMCP

      gzarog
      F
      license
      Not graded
      quality
      D
      maintenance
      A multi-platform fitness MCP server that syncs data from Garmin, Strava, Google Fit, and Suunto into a local DuckDB database and provides analytics tools via MCP.
      1
      -

    • Athlete MCP

      chamilqs
      A
      license
      Not graded
      quality
      C
      maintenance
      An open-source, Strava-first remote MCP server that enables users to authorize with Strava and ask AI about their training data.
      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

    B3.3/5.0

    Scored across 29 tools

    Disambiguation2/5

    Several tools overlap heavily: strava_data_inventory and strava_capabilities both describe supported data, privacy boundaries, and recommended workflows; connection_status, privacy_audit, and cache_status have overlapping status/privacy checks; get_activity_streams and activity_series both expose time-series data. Core data tools are mostly distinct, but the meta/status cluster creates real selection ambiguity.

    Naming Consistency3/5

    All tools share the strava_ prefix and snake_case, but the post-prefix pattern is inconsistent: verb-first names like list_activities and get_athlete coexist with noun-first names like profile_get and profile_update and pure nouns like daily_summary, activity_series, and onboarding. This mix is still readable but does not follow a predictable verb_noun convention throughout.

    Tool Count2/5

    29 tools is above the comfortable range, and many are meta/status/setup tools such as data_inventory, capabilities, agent_manifest, quickstart, demo, connection_status, cache_status, and privacy_audit that could be consolidated. The core Strava data surface is broad, but the extra support and onboarding tools bloat the set.

    Completeness4/5

    The set covers OAuth lifecycle, athlete/profile/activity/route/club/gear reads, streams, summaries, and training context, so most agent workflows are supported. Minor gaps remain, such as no activity upload/create/update and no club detail or segment/effort endpoints, but these are not central to the apparent read and training-analysis purpose.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues

    Resources