How to Use the Node-RED MCP in OpenAI Agents SDK

Q: How do I connect the Node-RED MCP Server to the OpenAI Agents SDK?

Install openai-agents first. Initialize the server using MCPServerStreamableHttp pointing to your Vinkius endpoint, and pass it to your Agent constructor in the mcpservers list. Set cacheToolsList=True to speed up startup times.

Q: Can my agent delete individual tabs using Node-RED and OpenAI Agents SDK?

Yes. The agent uses the deleteflow tool by passing the specific flow ID. It is best to have your agent call getflow first to double-check the target before running the deletion.

Q: What is the best way to modify a single node instead of the whole workspace?

Use the updateflow tool to target a single tab instead of replacing everything. This prevents configuration drift and keeps your other active flows running without interruption.

Deploy production-grade Node-RED flow modifications and monitoring via the OpenAI Agents SDK with built-in guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Node-RED MCP to OpenAI Agents SDK

Create your Vinkius account to connect Node-RED to OpenAI Agents SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Node-RED with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Edit active flows using OpenAI Agents SDK

The `set_flows` tool modifies your active Node-RED configuration instantly from your python code. Your agent reads the current setup first with `get_flows` to make sure it doesn't overwrite critical production wiring. Using the OpenAI Agents SDK lets you set up guardrails that intercept these calls before they run. If the agent tries to deploy a malformed JSON payload, the SDK blocks the execution before it hits your runtime.

Monitor server health via the MCP Server

The `get_diagnostics` tool checks the Node-RED memory, JS heap, and system metrics on demand. Running this tool lets your agent perform sanity checks after deploying new logic. This MCP Server integration feeds real-time performance data straight into OpenAI's tracing dashboard. You'll see exactly when a flow modification correlates with a spike in memory usage.

Install custom nodes programmatically

The `install_node` tool adds missing node modules to your palette without requiring terminal access. Checking what is currently running using `get_nodes` happens before any setup. If a specific integration node is missing, the agent installs it and then configures the new flow using `add_flow`. You don't have to SSH into the box just to run npm installs anymore.

Setup guide

Set up Node-RED MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Node-RED tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Node-RED tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Node-RED tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Node-RED Agent",
            instructions="You have access to Node-RED tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Node-RED. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Node-RED now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Node-RED MCP in OpenAI Agents SDK

Install `openai-agents` first. Initialize the server using `MCPServerStreamableHttp` pointing to your Vinkius endpoint, and pass it to your Agent constructor in the `mcp_servers` list. Set `cacheToolsList=True` to speed up startup times.

Yes. The agent uses the `delete_flow` tool by passing the specific flow ID. It is best to have your agent call `get_flow` first to double-check the target before running the deletion.

Route tasks between specialized agents inside your SDK setup. One agent can focus on reading diagnostics via `get_diagnostics`, while a more privileged agent handles write operations like `update_flow` with strict validation.

Use the `update_flow` tool to target a single tab instead of replacing everything. This prevents configuration drift and keeps your other active flows running without interruption.

All flow configurations, node credentials, and environment variables are protected. Vinkius runs this MCP Server inside an isolated sandbox, meaning your automation logic never leaks. Every connection requires a single secure token.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript