garmin-connect-plugin-for-dsh
Connect Garmin Connect fitness, health, and workout data to DeepSeek Harness and MCP agents.
Install
No clear install command was found in the current repository evidence.
Plugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Query recent activities (running, cycling, swimming, etc.) with compact or full detail
- Retrieve sleep scores, sleep stage breakdowns, daily steps, heart rate metrics, and body composition data
- Preview and create structured Garmin workouts using a two-call confirmation workflow
- Safely download and extract original activity FIT files to isolated local directories
- Provide running training philosophy advice (Hansons, Jack Daniels VDOT, Norwegian, Polarized) with mandatory intake checks
- Operate as a DeepSeek Harness plugin and as a standalone Model Context Protocol (MCP) server
Useful For
- Querying wearable fitness trends, sleep quality, and resting heart rate through natural language prompts
- Drafting and syncing structured interval and threshold workouts to Garmin Connect accounts
- Archiving raw FIT activity files to a local host directory for offline telemetry analysis
- Interfacing Garmin data with coding assistants such as Claude Code, OpenAI Codex, Windsurf, and Cursor via MCP
Who It Fits
- Athletes and runners tracking training data through DeepSeek Harness
- Developers looking to query personal Garmin health metrics via MCP tools
- Fitness coaches and enthusiasts seeking AI-assisted training plan generation
Documented Limitations
- Browser-based MFA/two-step verification is an unfinished developer preview and not officially supported for production
- Enforces process isolation (one account session per running process; in-process multi-tenant switching is not yet supported)
- Relies on unofficial Garmin Connect DI/SSO endpoints rather than an official public developer OAuth API
- FIT download requires explicit host directory configuration via GARMIN_FIT_DOWNLOAD_DIR
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 9 runtime, 8 development, 1 peer, and 1 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
package.json declares a prepare lifecycle script that may run during relevant package installation workflows.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- Likenttt/garmin-connect-plugin-for-dsh
- Registry source
- Community submission
- Registry classification
- Plugin
- Source checked
- 3427b06 · 2026-08-22
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 10GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-08-21
- Last release
- 2026-08-21
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
DeepSeek Harness plugin that bridges a local-shell-mcp service into DSH with shell, file, browser, remote-worker, and Live Workspace tools.
View plugin →Preview, create, and edit spreadsheets, docs, slides, and canvases in DeepSeek Harness powered by Univer.
View plugin →A DeepSeek Harness bridge that runs unmodified Pi ecosystem extensions as native DSH plugins.
View plugin →DeepSeek Harness plugin bundle that connects DSH to the self-hosted SandBase Harness agent runtime through MCP.
View plugin →