---
title: "Deploy n8n-mcp (MCP Server for n8n Workflows)"
description: "MCP server that lets Claude, Cursor & AI agents build and run n8n workflows"
category: "AI/ML"
url: https://railway.com/deploy/n8n-mcp-mcp-server-for-n8n-workflows
---

# Deploy n8n-mcp (MCP Server for n8n Workflows)

MCP server that lets Claude, Cursor & AI agents build and run n8n workflows

**[Deploy n8n-mcp (MCP Server for n8n Workflows) on Railway](https://railway.com/template/n8n-mcp-mcp-server-for-n8n-workflows)**

Machine-readable deploy manifest (JSON, validated by TemplateCI): https://railway.com/deploy/n8n-mcp-mcp-server-for-n8n-workflows/manifest.json

- **Creator:** Nick K's Projects
- **Category:** AI/ML
- **Total deploys:** 1

## Template content

### n8n-mcp https://cdn.jsdelivr.net/gh/homarr-labs/dashboard-icons/svg/n8n.svg

- **Image:** ghcr.io/czlonkowski/n8n-mcp-railway:latest
- **Health check:** /health
- **Public domain:** Yes

## Documentation

# Deploy and Host n8n-mcp on Railway

n8n-mcp is a Model Context Protocol (MCP) server that gives AI assistants deep knowledge of n8n. It ships with documentation, schemas and examples for 500+ n8n nodes, so Claude Desktop, Claude Code, Cursor, Windsurf or any MCP client can look up node parameters, validate configurations and — when connected to your n8n instance — create, update and run workflows for you. Stop copy-pasting JSON into n8n; describe the automation and let the agent build it correctly.

## About Hosting n8n-mcp

This template deploys the official Railway-optimised image `ghcr.io/czlonkowski/n8n-mcp-railway` as a single HTTP service with a public domain. It runs in `MCP_MODE=http`, protected by a generated `AUTH_TOKEN` that you paste into your MCP client. The node database is bundled in the image, so it works instantly with zero external dependencies. To enable workflow management (not just documentation), set `N8N_API_URL` to your n8n instance and `N8N_API_KEY` from n8n → Settings → API. Pair it with the n8n template on Railway and reference `https://${{n8n.RAILWAY_PUBLIC_DOMAIN}}` for a fully private setup. It is lightweight (under 256 MB RAM) and stateless.

## Common Use Cases

- Let Claude Code / Cursor build and fix n8n workflows from natural language
- Validate node configurations before deploying automations
- Search 500+ n8n nodes and their parameters without leaving your editor
- Create, update and trigger workflows on your n8n instance via MCP tools

## Dependencies for n8n-mcp Hosting

- Docker image `ghcr.io/czlonkowski/n8n-mcp-railway:latest`
- Optional: an n8n instance URL + API key for workflow management

### Implementation Details

Claude Code:

```bash
claude mcp add --transport http n8n-mcp https:///mcp --header "Authorization: Bearer "
```

Claude Desktop / Cursor (`mcpServers`):

```json
{ "n8n-mcp": { "url": "https:///mcp", "headers": { "Authorization": "Bearer " } } }
```

## Why Deploy n8n-mcp on Railway?


Railway is a singular platform to deploy your infrastructure stack. Railway will host your infrastructure so you don't have to deal with configuration, while allowing you to vertically and horizontally scale it.

By deploying n8n-mcp on Railway, you are one step closer to supporting a complete full-stack application with minimal burden. Host your servers, databases, AI agents, and more on Railway.


## Similar templates

- [Chat Chat](https://railway.com/deploy/-WWW5r) — Chat Chat, your own unified chat and search to AI platform.
- [stella](https://railway.com/deploy/stella) — Self-host stella with web, API, Postgres, Redis, and object storage.
- [Hermes Agent | OpenClaw Alternative with Dashboard](https://railway.com/deploy/hermes-agent-or-openclaw-alternative-wit) — Self-Hosted Hermes AI Agent for Telegram, Discord & Slack

Open this page in a browser: https://railway.com/deploy/n8n-mcp-mcp-server-for-n8n-workflows