Enterprise DNA
M MCP Servers Developer low

anup-shesh/garmin-local-mcp

by Various

Local-first Garmin data warehouse with an analysis-grade MCP server. Sync once, analyze forever - even when the API is down.

A

MCP

anup-shesh/garmin-local-mcp

Added 13 July 2026

#claude #garmin #garmin-connect #health #local-first #mcp #mcp-server #model-context-protocol

Overview

Local-first Garmin data warehouse with an analysis-grade MCP server. Sync once, analyze forever even when the API is down.

Best for

Best for
Developers who want to locally archive and analyze their Garmin health data without relying on the API

Use cases

  • Store Garmin health data locally for long-term analysis
  • Run queries against personal fitness data without live API dependency
  • Build custom dashboards or apps on top of synced Garmin data

How to use

Install

uvx garmin-local-mcp --help

Tools exposed

  • auth_status
  • sync_status
  • get_day
  • query_metrics
  • list_activities
  • get_activity
  • import_fit
  • request_delay_seconds
  • baseline_window_days
  • GARMIN_MCP_DATA_DIR

Tested with

Claude Desktop, Claude Code, Cursor

Example client config

{\n  "mcpServers": {\n    "garmin": {\n      "command": "garmin-local-mcp",\n      "args": ["serve"]\n    }\n  }\n}

Notes

Local-first Garmin data warehouse with an analysis-grade MCP server. Sync once, analyze forever even when the API is down.

2 stars on GitHub. Last updated 2026-07-11. Licensed MIT.

Use cases

  • Store Garmin health data locally for long-term analysis
  • Run queries against personal fitness data without live API dependency
  • Build custom dashboards or apps on top of synced Garmin data

Pros

  • Local-first design ensures privacy and offline access
  • Analysis-grade MCP server supports standard tool integration
  • Sync once and remain independent of API availability

Cons

  • Very new with only 2 GitHub stars, indicating limited community adoption
  • Requires Python environment setup and configuration
  • Documentation and stability may be minimal at this stage

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.

Pros

  • Local-first design ensures privacy and offline access
  • Analysis-grade MCP server supports standard tool integration
  • Sync once and remain independent of API availability

Cons

  • Very new with only 2 GitHub stars, indicating limited community adoption
  • Requires Python environment setup and configuration
  • Documentation and stability may be minimal at this stage
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

Running a business, not writing the code? See the MCP servers picked for operators, and get your first one wired up with us.

Operator picks