This project provides an MCP (Model Context Protocol) server that bridges AI assistants with n8n workflows, enabling natural language control over workflow management and execution. It targets developers and AI users seeking to automate and integrate n8n's powerful workflow capabilities into AI-driven applications.

How It Works

The server exposes a RESTful API that translates AI assistant commands into n8n API calls. It supports managing workflows (list, create, update, delete, activate, deactivate) and executions (run, monitor, get status). A key feature is the run_webhook tool, which allows triggering n8n workflows via their webhook endpoints, simplifying execution and enabling webhook authentication using provided credentials.

Quick Start & Requirements

• Install: npm install -g n8n-mcp-server or via Docker.
• Prerequisites: Node.js 18+, an n8n instance with API access enabled.
• Configuration: Requires setting N8N_API_URL and N8N_API_KEY via environment variables or a .env file. Webhook credentials (N8N_WEBHOOK_USERNAME, N8N_WEBHOOK_PASSWORD) are optional.
• AI Integration: Requires configuring AI assistants (e.g., VS Code Claude extension) with the absolute path to the built index.js file.
• Docs: n8n API Access

Highlighted Details

• Enables AI assistants to perform CRUD operations on n8n workflows.
• Supports executing workflows via both direct API calls and webhooks.
• Provides tools for listing, getting, creating, updating, deleting, activating, and deactivating workflows.
• Offers execution management including running, stopping, and retrieving execution details.

Maintenance & Community

The project is maintained by leonardsellem. Further community or roadmap information is not detailed in the README.

Licensing & Compatibility

• License: MIT
• Compatibility: Permissive MIT license allows for commercial use and integration with closed-source applications.

Limitations & Caveats

The README specifies that the run_webhook tool requires webhook-triggered workflows in n8n with Basic Authentication configured. Integration with AI assistants requires manual configuration of absolute paths to the built server file.