node-red

Connects Node-RED to LLMs via the Model Context Protocol (MCP) for intelligent AI workflows.

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

Command

claude mcp add --transport stdio moisesfreitas-seven-node-red-mcp-server node server.js \
  --env MCP_API_KEY="API key for authenticating with MCP (if required)" \
  --env MCP_ENDPOINT="Endpoint for MCP server (e.g., https://api.example.com/mcp)"

How to use

This MCP server enables Node-RED to interact with large language models and other AI services using the Model Context Protocol (MCP). It bridges Node-RED workflows with LLMs, allowing you to send prompts, manage contexts, and receive structured responses that can be composed into downstream nodes within your flows. The server exposes MCP endpoints that your Node-RED nodes can call to perform reasoning, context-aware questioning, and tool-assisted actions as part of automated intelligent workflows. With this server, you can orchestrate LLM calls alongside your existing Node-RED logic, enabling dynamic routing based on response content and contextual variables.

How to install

Prerequisites:

Node.js and npm installed on your system
A Node-RED environment if you plan to run flows locally
Access to an MCP endpoint (or use a local MCP instance) with any required API keys

Installation steps:

Install Node.js and npm from https://nodejs.org/
Install the MCP server package (example command if published to npm): npm install -g node-red-mcp-server
Verify installation by listing the installed package or running a help command (adjust to your package’s actual scripts): npm list -g | grep node-red-mcp-server
Create or update your MCP configuration file (see mcp_config below) and start the server: node server.js
In Node-RED, install any required HTTP request or MCP client nodes and configure them to point to the MCP server endpoints exposed by this service.

Note: If you publish this server under a different package name, adjust the npm install and startup commands accordingly.

Additional notes

Environment variables:

MCP_ENDPOINT should point to your MCP API endpoint.
MCP_API_KEY may be required for authentication; keep it secure.

Configuration tips:

Use descriptive server names in mcp_config to easily identify MCP backends in Node-RED flows.
If your MCP backend requires TLS or custom certificates, ensure Node.js trusts the CA or provide appropriate certs to the runtime.
Monitor logs for MCP request latencies and error codes to optimize prompt architecture and context handling.

Common issues:

Invalid MCP endpoint or missing API key: verify credentials and endpoint URL.
Network/firewall blocks between Node-RED and MCP backend: ensure proper routing and ports are open.
Mismatched MCP protocol versions: confirm compatibility between the server and client nodes in Node-RED.

Related MCP Servers

zen

1.1k

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.