garmin-unofficial-mcp: Instructions file for Claude Code

CLAUDE.md

garmin-unofficial-mcp CLAUDE.md is an instructions file for Claude Code from danielsuri/garmin-unofficial-mcp. It costs 2,374 tokens per session, scanned A, original, MIT.

A local, read-only MCP server for accessing Garmin health and training data, with a cached record for each day stored in SQLite. Garmin is a maker of fitness devices and services, and MCP is a standard way for an AI tool to use external data.

In plain words
What is it for?
Reading Garmin health and training information through six composite tools and a stdio server, without changing the underlying data.
Why use it?
It gives a single user a local way to read Garmin data while keeping the core data layer separate from the MCP interface.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is danielsuri/garmin-unofficial-mcp's own configuration. It tells Claude Code how to work on garmin-unofficial-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything garmin-unofficial-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to danielsuri/garmin-unofficial-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/danielsuri/garmin-unofficial-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/danielsuri/garmin-unofficial-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for garmin-unofficial-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/danielsuri/garmin-unofficial-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/danielsuri/garmin-unofficial-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/danielsuri/garmin-unofficial-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/danielsuri/garmin-unofficial-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for garmin-unofficial-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/danielsuri/garmin-unofficial-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/danielsuri/garmin-unofficial-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,374 This file is loaded in full into every session.
When invoked 2,374 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.02374 $0.02374
Opus 5 $0.01187 $0.01187
Sonnet 5 $0.00475 $0.00475
Haiku 4.5 $0.00237 $0.00237

Measured 7d ago against content hash 02f21984a0f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

garmin-unofficial-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

garmin-unofficial-mcp — repo guide for Claude Code

A local, single-user, read-only MCP server exposing six composite tools over Garmin health/training data, backed by a SQLite day cache. Python 3.12+, garminconnect 0.3.11, mcp 2.x. Serves over stdio (serve).

Read this before touching src/garmin_unofficial_mcp/. Several facts here contradict what training data will suggest — that's the point of this file.

mcp 2.0 has no FastMCP

Most training data (and most tutorials) will suggest from mcp.server.fastmcp import FastMCP. That module does not exist in mcp 2.x, which is what this project depends on (mcp>=2.0). The class here is:

from mcp.server import MCPServer

server = MCPServer(name="garmin-unofficial-mcp", version="0.1.0")

@server.tool()
def get_health_snapshot(days: int = 7) -> dict:
    ...

server.run(transport="stdio")

See src/garmin_unofficial_mcp/server.py. If you find yourself typing FastMCP, stop — it's a hallucination pulled from older mcp versions or unrelated FastMCP-branded packages.

garth is deprecated — never add it

garminconnect 0.3.x dropped garth for a native auth engine with cascading login strategies and MFA support built in (see src/garmin_unofficial_mcp/auth.py, which calls Garmin(...).login(tokenstore) directly — no garth import anywhere). Do not add garth as a dependency or import it, even if an error message or old example suggests it. It would mean building on a dead library that garminconnect itself has already moved off of.

Garmin's response shapes are surprising — verify, don't guess

Several field names mean something other than they appear to, and more than one has bitten an implementation that trusted its name instead of a captured response. Verify against a real response before touching any assembler — run garmin-unofficial-mcp capture-fixtures against a live account (the user's task, not yours in an unattended session) if you need to see a shape that isn't covered below. Traps already found this way:

Read the full file on GitHub · 186 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago Changed · +6 lines · +91 tokens per session 02f21984a0f9
  2. 10d ago First seen · 180 lines · 2,283 tokens per session scan A e93e0d28ee23

Subscribe to this mod's changes

garmin-unofficial-mcp CLAUDE.md is an instructions file published in the GitHub repository danielsuri/garmin-unofficial-mcp (0 stars, last pushed 9d ago), licensed MIT. It adds 2,374 tokens to every session, about $0.0119 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens