1. Conduid
  2. Automation
  3. N8n MCP Server
MCP server · Automation

N8n MCP Server

Unclaimed last commit 8 months ago automation
30Low

Scored 4 days ago · breakdown

About N8n MCP Server

N8n MCP Server is an MCP server published by harbouli in the Automation category.

The repository has 5 stars and 1 forks, with the last commit 8 months ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues before depending on it in production.

Install

From source
git clone https://github.com/harbouli/n8n-mcp-server

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about N8n MCP Server

Powered by Claude · Grounded in docs

I know everything about N8n MCP Server. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

Static checks derived from the repository just now. Heuristics on the source, not an audit.

  • ✓README presentThe repository ships documentation.
  • !License declaredNo license file. Legally you have no right to use it in a product.
  • !Tests presentNo tests found. Behaviour changes may go unnoticed between versions.
  • ✓Dependencies pinnedA lockfile pins dependency versions.
  • ✓No dynamic code executionSource scan found no eval, dynamic Function, or shell execution.

1 check has not been run yet.

README

n8n MCP Server

A Model Context Protocol (MCP) server that connects AI assistants (Claude, Cursor, etc.) to your n8n workflow automation instance. Manage, execute, and monitor n8n workflows through natural language.

Features

  • Workflow Management — List, create, update, delete, activate, and deactivate workflows
  • Workflow Execution — Run workflows directly via the REST API or through webhook triggers
  • Execution History — View, inspect, and manage past workflow executions
  • Tags & Diagnostics — List tags and check n8n connectivity
  • Type-safe — Fully written in TypeScript with proper error handling

Prerequisites

  • Node.js 18+ (20+ recommended)
  • A running n8n instance (self-hosted or cloud)
  • An n8n API key — generate one in n8n under Settings → API → Create API Key

Quick Start

1. Install dependencies

npm install

2. Configure

Copy the example env file and fill in your values:

cp .env.example .env

Edit .env:

N8N_BASE_URL=http://localhost:5678
N8N_API_KEY=your-api-key-here

3. Build

npm run build

4. Configure your MCP client

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "n8n": {
      "command": "node",
      "args": ["/absolute/path/to/n8n-mcp-server/build/index.js"],
      "env": {
        "N8N_BASE_URL": "http://localhost:5678",
        "N8N_API_KEY": "your-api-key-here"
      }
    }
  }
}

Cursor (.cursor/mcp.json)

{
  "mcpServers": {
    "n8n": {
      "command": "node",
      "args": ["/absolute/path/to/n8n-mcp-server/build/index.js"],
      "env": {
        "N8N_BASE_URL": "http://localhost:5678",
        "N8N_API_KEY": "your-api-key-here"
      }
    }
  }
}

Available Tools

Tool Description
list_workflows List all workflows with optional active/tag filters
get_workflow Get full details of a workflow (nodes, connections, settings)
create_workflow Create a new workflow with name, nodes, and connections
update_workflow Update an existing workflow
delete_workflow Permanently delete a workflow
activate_workflow Activate a workflow so it responds to triggers
deactivate_workflow Deactivate a workflow
execute_workflow Run a workflow directly via the REST API
execute_workflow_via_webhook Trigger a workflow through its webhook URL
list_executions List execution history with status/workflow filters
get_execution Get full execution details including run data
delete_execution Delete an execution from history
list_tags List all available tags
health_check Verify connectivity to the n8n instance

Usage Examples

Once connected, you can ask your AI assistant things like:

  • "List all my active n8n workflows"
  • "Show me the details of workflow 42"
  • "Create a new workflow called 'Daily Report' with a Schedule trigger and HTTP Request node"
  • "Execute workflow 15 with this input data: { "email": "test@example.com" }"
  • "Show me the last 10 failed executions"
  • "Activate workflow 7"
  • "Check if my n8n instance is reachable"

Development

# Run in development mode (no build needed)
npm run dev

# Build for production
npm run build

# Start production build
npm start

Architecture

n8n-mcp-server/
├── src/
│   ├── index.ts         # MCP server entry point & tool definitions
│   └── n8n-client.ts    # n8n REST API client
├── build/               # Compiled output (generated)
├── package.json
├── tsconfig.json
├── .env.example
└── README.md

Notes on Workflow Execution

n8n's public API (v1) does not include a direct "execute workflow" endpoint. This server provides two approaches:

  1. execute_workflow — Uses the internal /rest/workflows/{id}/run endpoint. Works on self-hosted instances. May require additional authentication configuration depending on your n8n setup.

  2. execute_workflow_via_webhook — Calls a workflow's webhook trigger URL. This is the officially recommended approach. Your workflow must have a Webhook node as its trigger and must be active.

Generating Your n8n API Key

  1. Open your n8n instance
  2. Go to Settings (bottom-left gear icon)
  3. Click API
  4. Click Create API Key
  5. Copy the key and add it to your .env or MCP client config

License

MIT

README fetched from the repository just now. The original is authoritative.

Questions

About N8n MCP Server

How do I install N8n MCP Server?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is N8n MCP Server safe to use with an AI agent?

Its trust score is 30 out of 100 (low). It passes 3 of the 5 static security checks run so far; the failures are listed above. It has no ConduID identity yet, so agent calls to it are not receipted.

Is N8n MCP Server still maintained?

The last commit was 8 months ago. That's long enough that you should check whether the maintainer is responding to issues before depending on it.