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.
curl -O https://raw.githubusercontent.com/akutishevsky/withings-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/akutishevsky/withings-mcpWrote 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.
[](https://agentmods.dev/instructions/akutishevsky/withings-mcp/claude-md)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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
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.
- today Changed · +10 lines · +1,161 tokens per session 3c52533cd2b1
- 10d ago First seen · 747 lines · 9,327 tokens per session scan A b9645177cb66
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.
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.
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.
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).
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.
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).
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.