mcp-n8n
MCP server for n8n API integration - Connect Claude AI to n8n workflows
claude mcp add --transport stdio ahmadsoliman-mcp-n8n-server npx -y @ahmad.soliman/mcp-n8n-server \ --env PROJECT_ID="" \ --env N8N_API_KEY="" \ --env N8N_HOST_URL=""
How to use
This MCP server exposes an interface to manage and trigger n8n workflows through the Model Context Protocol (MCP). It provides tools to list all available n8n workflows, inspect workflow webhooks, and invoke webhooks either via GET or POST requests. This makes it compatible with Claude Desktop and other MCP clients, enabling seamless integration for conversational agents or automation pipelines to interact with your n8n instance. Use the remote server configuration to connect via Claude or run locally with npm and connect from Claude Desktop.
Available tools include:
- list-workflows: retrieves all n8n workflows.
- list-workflow-webhooks: retrieves webhooks for a specific workflow (requires id parameter).
- call-webhook-get: calls a webhook using a GET request (requires url parameter).
- call-webhook-post: calls a webhook using a POST request (requires url and data parameters).
To use these with Claude or another MCP client, configure the MCP server in your client’s settings to point to this server (via npx or a local node path as shown in the installation notes) and pass the appropriate parameters to each tool when you want to list workflows, view webhooks, or trigger webhooks with data.
How to install
Prerequisites:
- Node.js and npm installed on your machine
- Access to install global npm packages or run via npx
Installation options:
- Global installation (recommended for remote usage)
- Run: npm install -g @ahmad.soliman/mcp-n8n-server
- Create or edit your .env with your n8n configuration (see Configuration below)
- Using with npx (no installation required)
- Run: npx -y @ahmad.soliman/mcp-n8n-server
- This spawns the MCP server on demand; ensure your environment variables are set as indicated in the Configuration section
- Local installation
- Clone the repository and install dependencies: git clone https://github.com/ahmadsoliman/mcp-n8n-server.git cd mcp-n8n-server npm install
- Start the server locally (after configuring .env): npm run mcp
Configuration (ENV):
- Create a .env file in your working directory and add the following variables: N8N_HOST_URL=https://your-n8n-instance.com PROJECT_ID=your_project_id_here (optional for cloud instances) N8N_API_KEY=your_api_key_here
If you are running locally, ensure your N8N_HOST_URL points to a reachable n8n instance and that the API key has appropriate permissions.
Additional notes
Tips and common considerations:
- Ensure your .env file is loaded in the environment where the MCP server runs. When using npx or global install, you may need to export or prefix environment variables in your shell or deployment environment.
- The N8N_HOST_URL should be the base URL for your n8n instance (e.g., http://localhost:5678 or https://your-n8n.example.com). The N8N_API_KEY must have access to the n8n resources you intend to manipulate.
- PROJECT_ID is optional and only needed for certain cloud/n8n configurations. Include it if your instance requires it.
- When using Claude Desktop, update claude_desktop_config.json (or equivalent) to reference the MCP server with the appropriate command and arguments. If you run locally, you may point to a local node path or use npx as shown in the examples.
- If you encounter authentication or CORS errors from n8n, verify that the API key is valid and that the host URL is reachable from the environment running the MCP server.
Related MCP Servers
zen
Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage
MCP -Deepseek_R1
A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)
mcp-fhir
A Model Context Protocol implementation for FHIR
mcp
Inkdrop Model Context Protocol Server
mcp-appium-gestures
This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..
dubco -npm
The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.