garmin_mcp

An MCP server that connects to Garmin Connect (via the python-garminconnect library) and exposes fitness/health data and related operations as a large set of MCP tools for MCP-compatible clients (e.g., Claude Desktop). Includes an auth CLI to pre-authenticate and persist OAuth tokens for MFA and subsequent use.

Evaluated Mar 30, 2026 (22d ago)
Repo ↗ Ai Ml mcp fitness health garmin python data-integration
⚙ Agent Friendliness
52
/ 100
Can an agent use this?
🔒 Security
64
/ 100
Is it safe for agents?
⚡ Reliability
29
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
85
Documentation
70
Error Messages
0
Auth Simplicity
55
Rate Limits
10

🔒 Security

TLS Enforcement
80
Auth Strength
75
Scope Granularity
20
Dep. Hygiene
55
Secret Handling
85

Supports file-based secrets and advises avoiding credentials in MCP config after pre-auth; tokens persisted locally (e.g., ~/.garminconnect or a token path). No explicit discussion of TLS enforcement, data minimization, or fine-grained authorization scopes in the README. Rate-limit and error-handling guidance for safer automated retries is not documented.

⚡ Reliability

Uptime/SLA
0
Version Stability
45
Breaking Changes
35
Error Recovery
35
AF Security Reliability

Best When

You want a local MCP toolset to query your Garmin Connect data through an MCP client, and you can run a one-time/occasional pre-auth flow to handle Garmin login + possible MFA.

Avoid When

You need a hosted SaaS API with no local credentials/token handling, or you require strict rate-limit SLAs and clearly published API error codes for programmatic retries beyond MCP-level behavior.

Use Cases

  • Answer questions about recent activities and workout details
  • Retrieve health metrics such as steps, heart rate, sleep, stress, and respiration
  • Summarize training readiness, training status, and weekly health aggregates
  • Access gear/equipment, workouts, and training plans
  • Get user/profile, body composition, and related wellness data

Not For

  • Uploading large GPS-tracked activity details (GPS/chart data is intentionally skipped for performance)
  • Destructive operations without explicit care (e.g., delete endpoints are mentioned as destructive/skipped)
  • Environments where interactive MFA auth is impossible (without a pre-auth step)

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: Pre-auth via garmin-mcp-auth CLI (saves OAuth tokens to ~/.garminconnect or a configured token path) Environment-variable credentials (GARMIN_EMAIL, GARMIN_PASSWORD) for initial auth / interactive mode MFA handled during the pre-auth / interactive auth flow
OAuth: Yes Scopes: No

Authentication is handled for Garmin Connect by the garminconnect library and persisted OAuth tokens. The README advises configuring the MCP server without credentials after pre-auth.

Pricing

Free tier: No
Requires CC: No

Open-source tooling; costs are primarily infrastructure/runtime and any local compute used by the MCP server.

Agent Metadata

Pagination
pagination supported (for recent activities) per README feature list
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • MFA may require a one-time pre-auth step because MCP servers run without an interactive terminal
  • Token expiry is periodic (README suggests ~6 months), requiring re-auth with --force-reauth
  • Some high-data-volume endpoints (e.g., activity details with large GPS/chart data) are skipped; agents must use the lighter get_activity() tools instead
  • Claude Desktop may fail to spawn the process if uvx is not in PATH; use full path to uvx

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for garmin_mcp.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered