LAI N8N

A MCP for Claude Desktop / Claude Code / Windsurf / Cursor to build n8n workflows for you
  • typescript

0

GitHub Stars

typescript

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "f4bse-94-lai-n8n-mcp-smithery": {
      "command": "npx",
      "args": [
        "n8n-mcp"
      ],
      "env": {
        "MCP_MODE": "stdio",
        "LOG_LEVEL": "error",
        "N8N_API_KEY": "your-api-key",
        "N8N_API_URL": "https://your-n8n-instance.com",
        "WEBHOOK_SECURITY_MODE": "moderate",
        "DISABLE_CONSOLE_OUTPUT": "true",
        "SQLJS_SAVE_INTERVAL_MS": "10000",
        "N8N_MCP_TELEMETRY_DISABLED": "true"
      }
    }
  }
}

n8n-MCP is a Model Context Protocol server that gives AI assistants deep, structured access to n8n node documentation, properties, and operations. It enables Claude and other AI tools to understand 543 n8n nodes, their schemas, and how to use them in real-world automations, with pre-built data and templates to accelerate development and validation.

How to use

You connect your MCP client to n8n-MCP to query node details, fetch essential properties, explore templates, and validate workflows before deployment. Start by running the MCP server in stdio mode and configure your client to communicate via JSON-RPC over stdout. When you enable stdio mode, you ensure clean, machine-parseable messages without noisy logs that could interfere with AI parsing.

How to install

Prerequisites: Node.js installed on your system, Docker (if using the Docker option), and a working internet connection for first-time runs.

Option A: Use npx for a quick start

npx n8n-mcp

Basic configuration for Claude Desktop to run in stdio mode uses environment variables to control JSON-RPC output and logging.

{
  "mcpServers": {
    "n8n-mcp": {
      "command": "npx",
      "args": ["n8n-mcp"],
      "env": {
        "MCP_MODE": "stdio",
        "LOG_LEVEL": "error",
        "DISABLE_CONSOLE_OUTPUT": "true"
      }
    }
  }
}

Additional options

Option B: Run via Docker for isolation

Pull the container image and start in stdio mode with the same JSON-RPC friendly environment.

docker pull ghcr.io/czlonkowski/n8n-mcp:latest

Basic Docker-based stdio configuration for Claude Desktop

{
  "mcpServers": {
    "n8n-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "--init",
        "-e", "MCP_MODE=stdio",
        "-e", "LOG_LEVEL=error",
        "-e", "DISABLE_CONSOLE_OUTPUT=true",
        "ghcr.io/czlonkowski/n8n-mcp:latest"
      ]
    }
  }
}

Security notes and best practices

Never deploy or test production workflows directly with AI tools. Always create a copy of workflows, test in a development environment, and export backups before applying changes.

Privacy & telemetry

n8n-mcp collects anonymous usage statistics to improve the tool. You can opt out by configuring telemetry settings in your run environment.

n8n integration tips

If you are connecting to a local n8n instance from Docker, use the host URL (for example, http://host.docker.internal:5678) as the API URL. Credentials are optional; providing them enables workflow management capabilities in addition to documentation access.

Local n8n development and testing

For development, you can install dependencies, build, and run tests locally. Use the stdio mode for Claude Desktop communication and the http mode if you need remote access.

Available tools

tools_documentation

Query documentation for MCP tools and capabilities

list_nodes

List all n8n nodes with optional filtering

get_node_info

Get comprehensive information about a specific node

get_node_essentials

Return essential 10-20 properties and optional real-world examples from templates

search_nodes

Full-text search across node documentation with optional examples

search_node_properties

Find specific properties within nodes

list_ai_tools

List all AI-capable nodes (any node can be used as an AI tool)

get_node_as_tool_info

Get guidance on using any node as an AI tool

list_templates

Browse 2,709 templates with descriptions

search_templates

Text search across template names and descriptions

search_templates_by_metadata

Filter templates by complexity, setup time, services, audience

list_node_templates

Find templates using specific nodes

get_template

Get complete workflow JSON for import

get_templates_for_task

Curated templates for common automation tasks

validate_workflow

Validate workflows including AI agent validation

validate_workflow_connections

Check workflow structure and AI tool connections

validate_workflow_expressions

Validate n8n expressions

validate_node_operation

Validate node configurations with runtime profiling

validate_node_minimal

Quick validation for required fields

get_property_dependencies

Analyze property visibility conditions

get_node_documentation

Get parsed node documentation

get_database_statistics

View database metrics

n8n_create_workflow

Create new workflows in n8n

n8n_validate_workflow

Validate deployed workflows in n8n

n8n_autofix_workflow

Auto-fix common workflow errors

n8n_list_workflows

List workflows with filtering

n8n_trigger_webhook_workflow

Trigger workflows via webhook

n8n_get_execution

Get execution details by ID

n8n_list_executions

List executions with status

n8n_health_check

Check n8n API connectivity

n8n_diagnostic

Troubleshoot tooling visibility and config issues

n8n_health_check

Health check tool

n8n_list_available_tools

List all available management tools

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational