n8n
MCP server that provides tools and resources for interacting with n8n API
claude mcp add --transport stdio leonardsellem-n8n-mcp-server node /path/to/n8n-mcp-server/build/index.js \ --env DEBUG="true" \ --env N8N_API_KEY="YOUR_N8N_API_KEY" \ --env N8N_API_URL="http://your-n8n-instance:5678/api/v1" \ --env N8N_WEBHOOK_PASSWORD="your_webhook_password" \ --env N8N_WEBHOOK_USERNAME="your_webhook_username"
How to use
This MCP server provides a bridge between AI assistants and an n8n workflow automation instance. It exposes tools that let you list workflows, inspect a workflow, create new workflows, and trigger n8n webhooks to run workflows. The webhook tool enables invoking workflow executions via n8n's webhook endpoints with optional authentication. Other tools let you fetch details about workflows to help the AI decide which actions to take next, and to create or modify workflows when needed. To integrate with an AI assistant, point the assistant’s MCP configuration at the built server (build/index.js) and supply the required N8N_API_URL and N8N_API_KEY as environment variables. You can also configure webhook credentials if you plan to use webhook-triggered workflows.
How to install
Prerequisites:
- Node.js 20 or later
- An accessible n8n instance with API access enabled
Install from npm (recommended for quick start):
npm install -g @leonardsellem/n8n-mcp-server
After installation, build the project if you cloned the repo locally:
git clone https://github.com/leonardsellem/n8n-mcp-server.git
cd n8n-mcp-server
npm install
npm run build
Optionally install globally from the built source:
npm install -g .
Docker installation:
docker pull leonardsellem/n8n-mcp-server
Run with your n8n settings:
docker run -e N8N_API_URL=http://your-n8n:5678/api/v1 \
-e N8N_API_KEY=your_n8n_api_key \
-e N8N_WEBHOOK_USERNAME=username \
-e N8N_WEBHOOK_PASSWORD=password \
leonardsellem/n8n-mcp-server
Additional notes
Environment variables:
- N8N_API_URL: Full URL to the n8n API including /api/v1
- N8N_API_KEY: API key for authenticating with n8n
- N8N_WEBHOOK_USERNAME/N8N_WEBHOOK_PASSWORD: Optional if you plan to use webhook-triggered workflows
- DEBUG: Enable verbose logging (true/false)
Tips:
- Ensure the path in mcp_config points to the built index.js file if you’re running from a local clone. Absolute paths are recommended.
- If you don’t plan to use webhooks, you can omit webhook-related env vars, but keep N8N_API_URL and N8N_API_KEY configured.
- When updating, rebuild and restart the MCP server to pick up changes.
Related MCP Servers
iterm
A Model Context Protocol server that executes commands in the current iTerm session - useful for REPL and CLI assistance
mcp
Octopus Deploy Official MCP Server
furi
CLI & API for MCP management
editor
MCP Server for Phaser Editor
DoorDash
MCP server from JordanDalton/DoorDash-MCP-Server
mcp
MCP сервер для автоматического создания и развертывания приложений в Timeweb Cloud