---
title: "Deploy Node-RED Context AI"
description: "AI workflows in Node-RED using Model Context Protocol (MCP)"
category: "AI/ML"
url: https://railway.com/deploy/node-red-mcp
---

# Deploy Node-RED Context AI

AI workflows in Node-RED using Model Context Protocol (MCP)

**[Deploy Node-RED Context AI on Railway](https://railway.com/template/node-red-mcp)**

- **Creator:** Moises's Projects
- **Category:** AI/ML
- **Total deploys:** 73

## Template content

### node-red https://nodered.org/about/resources/media/node-red-icon.png

- **Source:** https://github.com/moises-paschoalick/node-red-mcp-server
- **Health check:** /health
- **Public domain:** Yes

### bridge-mcp-server https://devicons.railway.com/i/nodejs.svg

- **Source:** https://github.com/moises-paschoalick/node-red-mcp-server
- **Health check:** /health
- **Public domain:** Yes

## Documentation

# Deploy and Host Node-RED (w/ MCP servers) on Railway

Node-RED MCP servers a visual automation environment that combines Node-RED with the Model Context Protocol (MCP), allowing you to build workflows using AI tools like OpenAI through a graphical interface. This template sets up both the Node-RED interface and the MCP backend required to process AI prompts.

## About Hosting Node-RED (w/ MCP servers)

This template deploys two services:
- A Node-RED instance with volume persistence to store flows
- A Node.js-based MCP host acts as a bridge, enabling integration with LLM providers such as OpenAI, Anthropic, Gemini, and OpenRouter through the MCP SDK.

After deployment, you must configure Node-RED to communicate with MCP Host:
1. Go to your deployed mcp-host service in Railway.
2. Copy the public URL (e.g. https://your-mcp-host.up.railway.app)
3. In the Node-RED UI, open the mcp-tools node configuration.
4. Paste the copied URL into the field labeled "URL do MCP Host".

This will allow Node-RED to communicate with the backend and execute AI prompts using the MCP protocol.

## Common Use Cases

- Build AI-powered workflows using a drag-and-drop interface
- Connect GPT agents with external tools visually
- Rapidly prototype AI applications with minimal backend code

## Dependencies for Node-RED (w/ MCP servers)

- The Railway template includes all required dependencies: Node.js runtime, mcp-host, and mcp-tools.


### Deployment Dependencies

- Node-RED
- @modelcontextprotocol/sdk
- node-red-contrib-mcp-tools

## Why Deploy node-red-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 node-red-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/node-red-mcp