How to Use the Node-RED MCP in LlamaIndex

Q: Can LlamaIndex search through individual Node-RED tabs?

Yes, the agent can use getflow to retrieve the JSON configuration of a single tab and index its contents. This allows you to perform semantic searches down to the individual node level.

Q: How does the Node-RED MCP Server help LlamaIndex prevent hallucinations?

The MCP server provides real-time facts via tools like getsettings and getdiagnostics. By forcing the agent to fetch live data before answering, you ensure responses are based on actual runtime state.

Index your Node-RED configurations into LlamaIndex to query flows, nodes, and diagnostics with semantic search.

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 LlamaIndex

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Semantic indexing of active flows

The `get_flows` tool retrieves your entire active Node-RED configuration so LlamaIndex can index it for semantic query processing. This lets your agent answer complex questions about how your integrations are wired together without manual inspection. By feeding the output of `get_flow` into a vector database, you create a searchable history of your automation logic. The agent can quickly find which flow handles a specific API endpoint by searching the indexed metadata.

Live diagnostics retrieval for LlamaIndex RAG

The `get_diagnostics` tool provides immediate metrics on Node-RED memory and JS engine health to ground your agent's decisions in live data. LlamaIndex uses this real-time context to answer performance queries accurately. Instead of guessing why an automation is slow, your query engine pulls current stats and matches them against historical logs. This approach eliminates hallucinated diagnoses by relying strictly on actual runtime telemetry.

Dynamic palette audits via MCP Server

The `get_nodes` tool lists all currently installed palette modules in your Node-RED instance for your agent to review. LlamaIndex parses this list to identify outdated or unused packages that might pose security risks. If a required module is missing, the agent executes `install_node` to fetch it immediately. Unused or risky modules can be discarded using `remove_node` to maintain a clean environment.

Setup guide

Set up Node-RED MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Node-RED MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Node-RED tools.",
)
response = await agent.run("List recent Node-RED data")

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 LlamaIndex

Initialize the MCP server client with your URL and wrap it in a `McpToolSpec` to expose the tools. Pass these tools to your LlamaIndex `FunctionAgent` to start querying and modifying your flows.

Yes, the agent can use `get_flow` to retrieve the JSON configuration of a single tab and index its contents. This allows you to perform semantic searches down to the individual node level.

The MCP server provides real-time facts via tools like `get_settings` and `get_diagnostics`. By forcing the agent to fetch live data before answering, you ensure responses are based on actual runtime state.

Yes, the agent can generate a new configuration and apply it using `add_flow` or `update_flow`. It can also use `set_flows` to replace the entire active configuration when a complete reset is needed.

Your flow JSON configurations and node lists are processed locally within your secure Vinkius MCP Server environment. Diagnostic logs and settings are never exposed to public vector stores or external third parties.

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