oeil-atelier-mcp

oeil-atelier-mcp

Serveur MCP exposant 4 ESP32-CAM d'atelier à Claude Code, permettant de lister les caméras, prendre des photos, consulter le statut technique et contrôler les LEDs flash.

Category
Visit Server

README

Œil dans l'atelier — Serveur MCP

Serveur MCP (Model Context Protocol) qui expose les 4 ESP32-CAM de l'atelier à Claude Code via stdio.

Installation

cd ~/projets/oeil-atelier-mcp
# (placer oeil_mcp_server.py et requirements.txt ici)

# Environnement virtuel Python (recommandé pour ne pas polluer le système)
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

Test manuel (vérifier que les imports passent)

source .venv/bin/activate
python3 -c "import mcp, httpx; print('OK')"

Déclaration dans Claude Code

Claude Code utilise un fichier de configuration pour déclarer les serveurs MCP.

claude mcp add oeil-atelier \
  /home/ch/projets/oeil-atelier-mcp/.venv/bin/python3 \
  /home/ch/projets/oeil-atelier-mcp/oeil_mcp_server.py

(Ajustez les chemins selon votre installation réelle.)

Outils exposés

  • list_cameras() : statut des 4 cams (en ligne / RSSI / uptime / LED)
  • get_camera_snapshot(camera_number) : photo instantanée d'une cam (1 à 4)
  • get_camera_status(camera_number) : statut technique détaillé
  • set_camera_led(camera_number, state) : on / off / toggle de la LED flash

Utilisation dans Claude Code

> Liste mes caméras d'atelier
> Regarde la cam-2 et dis-moi ce que tu vois
> Allume la LED de cam-3, attends 2s, puis prends un snapshot, puis éteins la LED

Dépannage

Logs du serveur : tout est écrit sur stderr (préfixe [oeil-mcp]). Visibles dans Claude Code via le panneau MCP, ou en lançant le serveur manuellement pour test.

mDNS qui ne répond pas : vérifier que avahi-daemon tourne :

systemctl status avahi-daemon
avahi-resolve -n cam-1.local

En dernier recours, remplacer cam-{}.local par les IP directes dans le code (constante CAMERA_HOSTNAME).

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured