mcp-n8n-server

MCP.Pizza Chef: ahmadsoliman

The mcp-n8n-server is an MCP server that provides seamless integration with n8n workflows through the Model Context Protocol. It allows listing and triggering n8n workflows with custom data, enabling AI models like Claude and other MCP clients to interact programmatically with n8n automation workflows. This server simplifies connecting AI-driven agents to powerful workflow automation without manual API handling, supporting flexible deployment via npm or npx and easy configuration through environment variables.

Use This MCP server To

List all available n8n workflows for AI-driven automation Trigger specific n8n workflows with custom input data Integrate Claude AI with n8n workflow automation Enable AI models to control and monitor n8n workflows Automate workflow execution from AI-powered MCP clients Connect AI agents to n8n for dynamic task orchestration

README

MCP n8n API Server

An mcp server that provides an interface to interact with n8n workflows through the Model Context Protocol (MCP).

Features

  • List all n8n workflows
  • Trigger specific workflows with custom data
  • Integration with Claude Desktop and other MCP clients

Installation

Global Installation (Recommended for Remote Usage)

npm install -g @ahmad.soliman/mcp-n8n-server

Then configure your n8n connection:

  1. Create a .env file in your working directory
  2. Add your n8n API information (see Configuration section below)

Using with npx (No Installation Required)

You can run the server directly with npx:

npx -y @ahmad.soliman/mcp-n8n-server

Local Installation

git clone https://github.com/ahmadsoliman/mcp-n8n-server.git
cd mcp-n8n-server
npm install

Configuration

Create a .env file with the following variables:

# n8n Host URL (required)
N8N_HOST_URL=https://your-n8n-instance.com

# n8n Project ID (optional - only needed for cloud instances)
PROJECT_ID=your_project_id_here

# n8n API Key (required)
N8N_API_KEY=your_api_key_here

Usage

As a Remote MCP Server

After installing globally, you can use it as a remote MCP server with Claude AI:

  1. Configure Claude AI to use this as a remote MCP server using the following JSON configuration:
{
  "mcpServers": {
    "n8n": {
      "command": "npx",
      "args": ["-y", "@ahmad.soliman/mcp-n8n-server"],
      "env": {
        "N8N_HOST_URL": "",
        "PROJECT_ID": "",
        "N8N_API_KEY": ""
      }
    }
  }
}
  1. Add the following to your prompt or instructions to Claude:
You have access to a remote MCP server for n8n integration. Use it to:
- List all n8n workflows
- Trigger webhooks and workflows
- Get information about available webhooks

As a Local MCP Server

You can run the server locally and connect to it from Claude Desktop:

# Start the server
npm start

Then configure Claude Desktop to use this MCP server:

Edit ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "n8n": {
      "command": "npx",
      "args": ["-y", "@ahmad.soliman/mcp-n8n-server"],
      "env": {
        "N8N_HOST_URL": "",
        "PROJECT_ID": "",
        "N8N_API_KEY": ""
      }
    }
  }
}

Alternatively, if you've cloned the repository locally:

{
  "mcpServers": {
    "n8n-server": {
      "command": "node",
      "args": ["/ABSOLUTE/PATH/TO/server-n8n/build/index.js"]
    }
  }
}

Setup

  1. Install dependencies:
npm install
  1. Configure environment variables:
  • Copy .env.example to .env (if not already done)
  • Update the following variables in .env:
    • N8N_API_URL: Your n8n instance URL (default: http://localhost:5678)
    • N8N_API_KEY: Your n8n API key
  1. Start the server:
# Start the MCP server (for integration with Claude Desktop and other MCP clients)
npm run mcp

For development with auto-reload:

npm run dev

MCP Tools (for LLM Integration)

The MCP server exposes the following tools for use with Claude Desktop or other MCP clients:

List Workflows

The list-workflows tool returns a list of all available n8n workflows.

List Workflow Webhooks

The list-workflow-webhooks tool returns all webhooks from a specific workflow.

Parameters:

  • id: The ID of the workflow to get webhooks from

Call Webhook (GET)

The call-webhook-get tool allows calling a webhook with a GET request.

Parameters:

  • url: The webhook URL to call

Call Webhook (POST)

The call-webhook-post tool allows calling a webhook with a POST request.

Parameters:

  • url: The webhook URL to call
  • data: Data to send in the POST request body

mcp-n8n-server FAQ

How do I install the mcp-n8n-server globally?
Run `npm install -g @ahmad.soliman/mcp-n8n-server` to install it globally for remote usage.
Can I run the mcp-n8n-server without installation?
Yes, you can run it directly using `npx -y @ahmad.soliman/mcp-n8n-server` without installing.
How do I configure the connection to my n8n instance?
Create a `.env` file with your `N8N_HOST_URL` and optional project ID and API key variables.
Which MCP clients are compatible with mcp-n8n-server?
It integrates with Claude Desktop and other MCP clients supporting the Model Context Protocol.
What workflows can I trigger using this server?
You can trigger any n8n workflow available in your connected n8n instance with custom data.
Is the mcp-n8n-server suitable for production environments?
Yes, it supports global installation and environment-based configuration for production use.
Does the server support secure API authentication?
Yes, you can configure API keys and other authentication methods via environment variables.
Can I extend the server to support additional n8n features?
The server is open source and can be extended to add more n8n API interactions as needed.