N8N MCP Server

N8N MCP Server

Enables management of multiple N8N workflow automation instances through MCP. Supports listing, creating, updating, deleting, executing workflows and monitoring their executions across different N8N environments.

Category
Visit Server

README

N8N MCP Server

Serveur MCP (Model Context Protocol) pour gérer plusieurs instances N8N depuis Claude, VSCode ou tout autre client MCP.

Fonctionnalités

11 outils MCP disponibles :

Outil Description
n8n_list_instances Lister les instances N8N disponibles
n8n_list_workflows Lister les workflows
n8n_search_workflows Rechercher des workflows
n8n_get_workflow Récupérer un workflow
n8n_create_workflow Créer un workflow
n8n_update_workflow Mettre à jour un workflow
n8n_delete_workflow Supprimer un workflow
n8n_toggle_workflow Activer/désactiver un workflow
n8n_execute_workflow Exécuter un workflow
n8n_list_executions Lister les exécutions
n8n_get_execution Détails d'une exécution

Modes de transport

Le serveur supporte deux modes de transport :

Mode Usage Variable
SSE (défaut) Déploiement sur Coolify/Docker MCP_TRANSPORT=sse
stdio Usage local (Claude Desktop) MCP_TRANSPORT=stdio

Installation

Prérequis

  • Node.js 18+
  • Une ou plusieurs instances N8N avec API activée

Installation locale

# Cloner le repository
git clone https://github.com/businessarchi/n8n-mcp-server.git
cd n8n-mcp-server

# Installer les dépendances
npm install

# Build
npm run build

Configuration

Variables d'environnement

Option 1 : Configuration JSON (recommandé pour plusieurs instances)

N8N_INSTANCES='[{"name":"prod","url":"https://n8n.example.com","apiKey":"your-api-key"},{"name":"dev","url":"https://n8n-dev.example.com","apiKey":"your-api-key"}]'

Option 2 : Configuration individuelle

# Instance 1
N8N_INSTANCE_1_NAME=prod
N8N_INSTANCE_1_URL=https://n8n.example.com
N8N_INSTANCE_1_API_KEY=your-api-key

# Instance 2
N8N_INSTANCE_2_NAME=dev
N8N_INSTANCE_2_URL=https://n8n-dev.example.com
N8N_INSTANCE_2_API_KEY=your-api-key

Option 3 : Instance unique

N8N_URL=https://n8n.example.com
N8N_API_KEY=your-api-key
N8N_INSTANCE_NAME=default

Générer une clé API N8N

  1. Aller dans SettingsAPI dans votre instance N8N
  2. Créer une nouvelle clé API
  3. Copier la clé et l'utiliser dans la configuration

Utilisation

Avec Claude Desktop (mode stdio)

Ajouter dans ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) ou %APPDATA%\Claude\claude_desktop_config.json (Windows) :

{
  "mcpServers": {
    "n8n": {
      "command": "node",
      "args": ["/chemin/vers/n8n-mcp-server/dist/index.js"],
      "env": {
        "MCP_TRANSPORT": "stdio",
        "N8N_INSTANCES": "[{\"name\":\"prod\",\"url\":\"https://n8n.example.com\",\"apiKey\":\"xxx\"}]"
      }
    }
  }
}

Avec un client MCP SSE (mode réseau)

Une fois déployé sur Coolify, le serveur expose :

Endpoint Description
GET / Informations sur le serveur
GET /health Health check
GET /sse Connexion SSE pour les clients MCP
POST /messages Envoi de messages au serveur

Configuration client MCP SSE :

{
  "mcpServers": {
    "n8n": {
      "transport": "sse",
      "url": "https://votre-serveur.coolify.io/sse"
    }
  }
}

Déploiement sur Coolify

Configuration Coolify

  1. Créer une nouvelle application dans Coolify
  2. Source : GitHub → Sélectionner ce repository
  3. Type de build : Dockerfile
  4. Port exposé : 3000

Variables d'environnement Coolify

N8N_INSTANCES=[{"name":"prod","url":"https://n8n.example.com","apiKey":"xxx"}]

Ou individuellement :

N8N_INSTANCE_1_NAME=prod
N8N_INSTANCE_1_URL=https://n8n.example.com
N8N_INSTANCE_1_API_KEY=your-api-key

Health Check

Configurer le health check vers /health sur le port 3000.

Développement

# Mode développement avec rechargement automatique
npm run dev

# Build
npm run build

# Démarrer en production (SSE par défaut)
npm start

# Démarrer en mode stdio
MCP_TRANSPORT=stdio npm start

Architecture

src/
├── index.ts        # Point d'entrée MCP Server (SSE + stdio)
├── config.ts       # Gestion de la configuration
├── n8n-client.ts   # Client API N8N
├── tools.ts        # Définitions des 11 outils MCP
└── types.ts        # Types TypeScript

Licence

MIT

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
Qdrant Server

Qdrant Server

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

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
E2B

E2B

Using MCP to run code via e2b.

Official
Featured