mon-serveur-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mon-serveur-mcpwhat's the weather in Paris?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Serveur MCP — mon-serveur-mcp
Serveur Model Context Protocol (MCP) exposant des outils système et météo à un LLM compatible MCP (ex. Claude Desktop).
Prérequis
Python 3.12+
mcp1.27+
Related MCP server: WEATHGARDS
Installation
python3 -m venv .venv
source .venv/bin/activate
pip install mcpLancement
python server.pyLe serveur communique via stdin/stdout (protocole MCP over stdio).
Outils disponibles
get_disk_usage
Calcule la taille totale d'un dossier en mégaoctets.
Paramètre | Type | Description |
| string | Chemin du dossier |
Exemple de réponse : 142.3 Mo
get_weather
Retourne la météo actuelle d'une ville via l'API Open-Meteo (gratuite, sans clé API).
Paramètre | Type | Description |
| string | Nom de la ville |
Exemple de réponse : Paris — 18.2°C, Partiellement nuageux, vent 14 km/h
list_files
Liste les fichiers et sous-dossiers d'un dossier local. Les dossiers sont affichés en premier ([D]), suivis des fichiers ([F]), triés alphabétiquement.
Paramètre | Type | Description |
| string | Chemin du dossier |
Exemple de réponse :
[D] documents
[D] images
[F] README.md
[F] server.py
[F] tools.pyStructure du projet
.
├── server.py # Serveur MCP : enregistrement des outils et point d'entrée
├── tools.py # Implémentation des outils
└── pyproject.tomlIntégration avec Claude Desktop
Ajouter dans claude_desktop_config.json :
{
"mcpServers": {
"mon-serveur-mcp": {
"command": "/chemin/vers/.venv/bin/python",
"args": ["/chemin/vers/server.py"]
}
}
}This server cannot be deployed
Maintenance
Related MCP Connectors
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
- UnifAPIOAuthcom.unifapi
Hosted MCP server for live public-data APIs and Skills for AI agents.
MCP server exposing the Backtest360 engine API as tools for AI agents.
Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources.
Related MCP Servers
- FlicenseAqualityDmaintenanceLightweight MCP server that exposes tools for system information and weather lookup, designed for agent integration via stdio.1-
- FlicenseNot gradedqualityDmaintenanceExposes MCP tools that enable remote LLMs to query local Docker containers, OS processes, and system services in real time.-
- AlicenseAqualityDmaintenanceProvides LLMs with local filesystem operations (read/write files, list directories) and command execution via MCP, enabling file management and task automation within AI clients.79 npmISC
- FlicenseNot gradedqualityDmaintenanceEnables AI agents and users to manage workspace files, monitor system metrics, take persistent notes, and retrieve weather data via MCP tools and resources.-