devices-mcp CLAUDE.md

devices-mcp CLAUDE.md is an instructions file for Claude Code from sandraschi/devices-mcp. It costs 200 tokens per session, scanned A, original, MIT.

Project instructions for devices-mcp, a local server that connects an AI coding agent to cameras, lights, safety devices and weather services. It supports desktop connections and a web application.

In plain words
What is it for?
Use them when developing, running or connecting to the devices-mcp IoT and surveillance dashboard.
Why use it?
They give the agent the correct ways to start the server, communicate with it and use its ports, reducing setup mistakes.

Instructions file for Claude Code

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

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/sandraschi/devices-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/sandraschi/devices-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 devices-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sandraschi/devices-mcp/claude-md.svg)](https://agentmods.dev/instructions/sandraschi/devices-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sandraschi/devices-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sandraschi/devices-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 200 This file is loaded in full into every session.
When invoked 200 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00200 $0.00200
Opus 5 $0.00100 $0.00100
Sonnet 5 $0.00040 $0.00040
Haiku 4.5 $0.00020 $0.00020

Measured 5d ago against content hash c9d9bbc05942, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

devices-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 5d 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 · 20 lines

What it actually says

devices-mcp -- Claude Code Guide

Overview

FastMCP 3.4+ server for universal IoT and surveillance dashboard: cameras (Tapo, Ring, USB), Nest Protect, Hue lights, Netatmo weather, and more.

Entry Points

  • uv run python -m devices_mcp.server_v2 -- MCP stdio server
  • web-sota\start.ps1 -- Full webapp (FastAPI :10717 + Vite :10716)

Standards

  • FastMCP 3.4+ portmanteau tool pattern -- tools use operation enum param
  • Responses: structured dicts with success, message, domain-specific fields
  • Dual transport: stdio (Claude Desktop) + HTTP
  • See mcp-central-docs for fleet-wide coding standards

Ports

  • Backend: 10717
  • Frontend: 10716
  • USB camera helper: 10715
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. 5d ago First seen · 20 lines · 200 tokens per session scan A c9d9bbc05942

Subscribe to this mod's changes

devices-mcp CLAUDE.md is an instructions file published in the GitHub repository sandraschi/devices-mcp (2 stars, last pushed 3d ago), licensed MIT. It adds 200 tokens to every session, about $0.0010 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