How to Use the Node-RED MCP in Google ADK

Q: How do I register the Node-RED MCP Server inside Google ADK?

Install the google-adk package and initialize McpToolset with your HTTP server parameters. Pass this toolset to your LlmAgent instance to make all 11 tools instantly available to Gemini.

Q: Can I restrict which Node-RED tools the Google ADK agent can access?

Yes. You can pass a filtered list of tool names to your McpToolset configuration. This is highly recommended if you want to allow reading flows with getflows but block destructive actions like deleteflow.

Q: How do I handle runtime settings updates?

Use getsettings to read the active configuration limits. While you cannot write to settings directly, your agent can use this information to adjust how it deploys new flows via addflow.

Connect Gemini models to your Node-RED deployment using the Google ADK to analyze and modify flows over massive contexts.

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 Google ADK

Create your Vinkius account to connect Node-RED to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run automated flow updates via Google ADK

The `update_flow` tool lets your Gemini agent modify active automation paths based on enterprise data triggers. Running `get_flow` first lets the agent inspect the targeted tab before applying updates. This MCP setup works well when you feed BigQuery logs into Gemini. By reviewing logs, the agent spots errors in your physical automation and rewrites the Node-RED flows.

Manage palette nodes using this MCP Server

The `install_node` tool adds npm packages to your runtime on the fly. Checking for existing modules with `get_nodes` prevents redundant downloads. If you need to clean up unused packages, the agent runs `remove_node` to keep your environment lightweight. This keeps your container footprints small and reduces the attack surface of your server.

Track system diagnostics directly

The `get_diagnostics` tool fetches current CPU and memory metrics from your Node-RED instance. Checking these stats before deploying heavy workloads keeps your server stable. Gemini's massive context window lets you pass months of historical runtime metrics alongside the current `get_settings` output. Spotting trends that lead to memory exhaustion becomes straightforward.

Setup guide

Set up Node-RED MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Node-RED tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Node-RED_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Node-RED tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Install the `google-adk` package and initialize `McpToolset` with your HTTP server parameters. Pass this toolset to your `LlmAgent` instance to make all 11 tools instantly available to Gemini.

Yes. You can pass a filtered list of tool names to your `McpToolset` configuration. This is highly recommended if you want to allow reading flows with `get_flows` but block destructive actions like `delete_flow`.

Yes. You can feed entire multi-megabyte flow configurations retrieved by `get_flows` directly into the prompt. Gemini analyzes the entire system architecture at once without running out of memory.

Use `get_settings` to read the active configuration limits. While you cannot write to settings directly, your agent can use this information to adjust how it deploys new flows via `add_flow`.

Your active flow JSON files and palette settings remain completely private. Vinkius runs this MCP Server in an isolated sandbox with zero-trust network rules. No data is stored or shared externally.

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