n8n

This MCP server exposes n8n workflow automation via the Model Context Protocol, allowing AI assistants to manage and interact with your n8n instance through natural language prompts. It provides tools to list, create, update, and delete workflows; execute workflows and inspect execution history; manage tags and webhooks; and fetch credentials in a read-only fashion. The integration is designed so that an agent (like Claude) can query workflows, run automations, and retrieve results by calling the appropriate MCP tools such as list_workflows, create_workflow, execute_workflow, get_executions, and get_workflow_webhooks. Configure the server with your n8n instance URL and API key, then use the Claude Desktop (or other MCP-enabled client) to connect and issue tool requests against your n8n data model via the MCP interface.

Prerequisites:

• Node.js 18 or higher
• npm (comes with Node.js)
• An n8n instance with API access enabled and a valid API key

Installation steps:

1. Install from npm (global):

npm install -g n8n-mcp-server

2. Or install from source:

git clone https://github.com/nikolausm/n8n-mcp-server.git
cd n8n-mcp-server
npm install
npm run build

3. Run the MCP server (example):

npx n8n-mcp-server

4. Ensure your n8n instance URL and API key are available to the MCP server via environment variables or configuration as described in the README.

• Keep your n8n API key secure; avoid committing keys. Use environment variables in production.
• The MCP server runs with the same permissions as the provided API key in n8n.
• If you deploy behind a proxy or firewall, ensure the MCP server can reach your n8n instance and that CORS or API access controls allow the MCP client.
• For cloud n8n instances, set N8N_URL to your cloud URL and N8N_API_KEY to a valid API key with appropriate permissions.
• When building from source, run npm run build to generate dist/index.js used by the MCP server.
• Refer to the n8n API documentation for supported endpoints and data shapes to craft correct tool inputs.