How to Use the Node-RED MCP in AutoGen

Q: How do I register the Node-RED MCP Server with AutoGen?

Use the StreamableHttpServerParams to connect to your MCP server and fetch the tools. You can then pass the tool list directly to your AutoGen AssistantAgent to enable multi-agent flow management.

Q: Can AutoGen agents safely modify active Node-RED configurations?

Yes, agents can use getflows to audit the current state and then propose updates. By using updateflow instead of overwriting everything, they can make precise, safe changes to individual tabs.

Q: How do AutoGen agents handle Node-RED deployment errors?

If a flow fails to deploy, the agents can query getdiagnostics to check system health. They will discuss the error logs and automatically attempt to resolve the issue using updateflow or deleteflow.

Q: Can AutoGen replace the entire Node-RED workspace?

Yes, the agents can use setflows to deploy a completely new configuration. Because this is a destructive action, you should configure a human-in-the-loop agent to approve the final decision.

Let your AutoGen agents debate and coordinate Node-RED flow deployments and diagnostic audits safely.

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 AutoGen

Create your Vinkius account to connect Node-RED to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-driven flow deployment

The `add_flow` tool allows your AutoGen developer agent to propose new automation flows directly to the Node-RED runtime. Before applying, a separate reviewer agent inspects the JSON payload to check for configuration errors. By requiring a debate before running `update_flow`, you prevent broken code from taking down your active integrations. The agents negotiate the changes, ensuring only validated configurations are deployed to the system.

Multi-agent system audits via MCP Server

The `get_diagnostics` tool delivers real-time memory and JS engine metrics to your AutoGen monitoring agents. When a performance spike is detected, the agents discuss the root cause based on live telemetry. An operations agent can propose running `get_flows` to see which active flow is consuming resources. The team of agents then decides whether to suspend the offending flow or scale the environment.

Collaborative palette management

The `get_nodes` tool provides a complete list of installed palette modules for your agents to analyze. A security agent can flag unauthorized packages, while a developer agent defends the need for specific tools. Once they reach a consensus, the agents use `install_node` to add approved modules or `remove_node` to delete risky ones. This automated negotiation keeps your Node-RED runtime secure and optimized.

Setup guide

Set up Node-RED MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Node-RED tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Node-RED_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Node-RED data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Node-RED_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Node-RED data")
    print(result.messages[-1].content)

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 AutoGen

Use the `StreamableHttpServerParams` to connect to your MCP server and fetch the tools. You can then pass the tool list directly to your AutoGen `AssistantAgent` to enable multi-agent flow management.

Yes, agents can use `get_flows` to audit the current state and then propose updates. By using `update_flow` instead of overwriting everything, they can make precise, safe changes to individual tabs.

If a flow fails to deploy, the agents can query `get_diagnostics` to check system health. They will discuss the error logs and automatically attempt to resolve the issue using `update_flow` or `delete_flow`.

Yes, the agents can use `set_flows` to deploy a completely new configuration. Because this is a destructive action, you should configure a human-in-the-loop agent to approve the final decision.

No, all communication between AutoGen and the Node-RED runtime happens through secure, encrypted endpoints in your Vinkius MCP Server environment. Your flow structures, settings, and diagnostic metrics remain strictly confidential.

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