withings-mcp: Instructions file for Claude Code

CLAUDE.md

withings-mcp CLAUDE.md is an instructions file for Claude Code from akutishevsky/withings-mcp. It costs 10,488 tokens per session, scanned A, original, MIT.

Repository instructions for a server that connects Claude to Withings health data through an MCP connection. Withings is a health-device service, and OAuth is a standard method for authorizing access without sharing a password.

In plain words
What is it for?
Use them when developing, checking, building, or deploying the Bun and TypeScript server.
Why use it?
They document the project’s architecture, commands, authentication, and deployment setup so changes can be made safely and consistently.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions subagents; names the TodoWrite tool.

This is akutishevsky/withings-mcp's own configuration. It tells Claude Code how to work on withings-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 withings-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to akutishevsky/withings-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/akutishevsky/withings-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/akutishevsky/withings-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 withings-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/akutishevsky/withings-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/akutishevsky/withings-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/akutishevsky/withings-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/akutishevsky/withings-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 withings-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/akutishevsky/withings-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/akutishevsky/withings-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10,488 This file is loaded in full into every session.
When invoked 10,488 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 $0.10488 $0.10488
Opus 5 $0.05244 $0.05244
Sonnet 5 $0.02098 $0.02098
Haiku 4.5 $0.01049 $0.01049

Measured today against content hash 3c52533cd2b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

withings-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 today.

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 · 757 lines

How it starts

The opening of the file, as written. The whole thing — 757 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

General Rules

Always execute tasks in parallel when possible. If multiple independent operations need to be performed (e.g., reading files, running searches, editing unrelated files, running builds), do them simultaneously rather than sequentially. Only run tasks sequentially when there is a dependency between them.

Project Overview

This is an MCP (Model Context Protocol) server that integrates Withings health data with Claude. It implements OAuth 2.0 authentication with PKCE support and uses the Streamable HTTP transport (via the SDK's WebStandardStreamableHTTPServerTransport) for communication between MCP clients and the server.

Development Commands

Running

bun run start        # Run the server (Bun executes TypeScript directly)
bun run dev          # Hot-reload mode for local development
bun run typecheck    # Type-check with tsc (no emit)
bun run build        # Bundle for production (outputs to ./build)

Deployment

Deployed to DigitalOcean App Platform, which detects Bun automatically via its buildpack and runs bun run start.

Architecture

Project Structure

The codebase is organized by context into focused modules:

src/
├── auth/                     # Authentication & Authorization
│   ├── oauth.ts             # OAuth 2.0 endpoints (/authorize, /callback, /token, /register)
│   ├── token-store.ts       # MCP ↔ Withings token mapping
│   └── session-store.ts     # MCP session ↔ owning token (restart survival)
├── db/                       # Database Layer (Supabase)
│   └── supabase.ts          # Supabase client initialization
├── server/                   # Server components
│   ├── app.ts               # Hono app setup, route mounting, MCP_ENDPOINT constant
│   ├── mcp-endpoints.ts     # Unified MCP handler for /mcp endpoint (GET/POST/DELETE)
│   ├── middleware.ts        # Bearer token authentication
│   └── rate-limiter.ts      # Rate limiting middleware using Supabase
├── tools/                    # MCP tools organized by Withings API category
│   ├── index.ts             # Registers all tools on MCP server instances
│   ├── sleep.ts             # Sleep API: get_sleep, get_sleep_summary, get_hrv
│   ├── measure.ts           # Measure API: get_measures, get_workouts, get_activity, get_intraday_activity
│   ├── user.ts              # User API: get_user_devices, get_user_goals
│   ├── heart.ts             # Heart API: list_heart_records, get_heart_signal
│   └── stetho.ts            # Stetho API: list_stetho_records, get_stetho_signal
├── withings/                # Withings API Integration
│   └── api.ts               # Withings API client & request handling
├── types/                    # TypeScript type definitions
│   ├── hono.ts              # Hono app environment types (AppEnv, AppContext)
│   └── withings.ts          # Withings API response interfaces & param types
├── utils/                    # Utilities
│   ├── logger.ts            # Privacy-safe custom logger for Deno Deploy
│   ├── encryption.ts        # AES-256-GCM encryption for sensitive tokens
│   └── timestamp.ts         # Timezone-aware timestamp conversion utilities
└── index.ts                 # Main entry point (initializes Supabase, stores & creates app)

public/
└── styles/                      # External CSS (no unsafe-inline CSP)
    ├── index.css               # Landing page styles
    └── health.css              # Health check page styles

supabase/
└── migrations/
    ├── 001_initial_schema.sql   # Database schema (tables, indexes)
    ├── 004_atomic_rate_limit.sql # Atomic rate limit PostgreSQL function
    ├── 005_pg_cron_cleanup.sql  # pg_cron jobs for expired record cleanup
    ├── 006_mcp_sessions.sql     # Persisted MCP sessions (survive restarts)
    ├── 007_token_rotation_grace.sql # previous_mcp_token grace window
    ├── 008_sliding_window_rate_limit.sql # sliding-window check_rate_limit()
    └── 009_rate_limit_window_clamp.sql   # clamp stale reset_time from a longer window

Read the full file on GitHub · 757 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. today Changed · +10 lines · +1,161 tokens per session 3c52533cd2b1
  2. 10d ago First seen · 747 lines · 9,327 tokens per session scan A b9645177cb66

Subscribe to this mod's changes

withings-mcp CLAUDE.md is an instructions file published in the GitHub repository akutishevsky/withings-mcp (42 stars, last pushed yesterday), licensed MIT. It adds 10,488 tokens to every session, about $0.0524 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 2026-08-30.

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

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

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