How to Use the ESPHome MCP in LlamaIndex

Q: How do I load ESPHome device states into LlamaIndex?

Use llama-index-tools-mcp with BasicMCPClient pointing to your Vinkius endpoint. Convert the tools using McpToolSpec so your agent can call getentitystate to populate its memory.

Q: Can LlamaIndex query historical ESPHome data?

Yes, by indexing the output of getmetrics and getentitystate over time. The agent searches this historical vector store to identify patterns in your hardware usage.

Q: How does LlamaIndex prevent hallucinations when running ESPHome actions?

The agent uses the getentitystate tool to verify the actual state of a device before running an action. This ensures it doesn't try to open a cover that is already open.

Q: Can I use LlamaIndex to control ESPHome climate entities?

You can use numberset and selectoption to adjust target temperatures and modes on your climate nodes. The agent decides on these values by retrieving context from your local environment documents.

Index ESPHome device states and metrics into LlamaIndex vector stores for retrieval-augmented IoT control.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ESPHome MCP to LlamaIndex

Create your Vinkius account to connect ESPHome 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 ESPHome with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Indexing live IoT states into LlamaIndex

The MCP Server exposes `get_entity_state` to pull live ESPHome sensor and switch states directly into your LlamaIndex document store. Your LlamaIndex agent queries this indexed data to answer questions about your home's current environment without hallucinating. By indexing these ESPHome states, your LlamaIndex RAG pipeline gets a historical log of device behaviors. When you ask why a room is hot, the agent pulls the latest `get_entity_state` data alongside your manuals to recommend an ESPHome `fan_action`.

Structured ESPHome metric retrieval and indexing

`get_metrics` fetches Prometheus metrics from your ESP32 micro-controllers to populate your LlamaIndex vector index with hardware performance data. LlamaIndex uses this data to track long-term trends in ESPHome node stability and WiFi signal strength. The LlamaIndex agent searches this performance index to diagnose connection drops before triggering an ESPHome `switch_action`. This grounds your automation decisions in physical hardware telemetry rather than static rules.

Grounded physical device execution via MCP Server tools

`cover_action` allows your LlamaIndex agent to physically adjust blinds or garage doors based on retrieved context. The agent searches your calendar or local weather index, then triggers the ESPHome cover action to match your preferences. You can also use `alarm_action` to secure your ESPHome partition when your LlamaIndex index indicates no one is home. The agent verifies the current state against its knowledge base before modifying the physical alarm panel.

Setup guide

Set up ESPHome 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 ESPHome 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 ESPHome tools.",
)
response = await agent.run("List recent ESPHome 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 ESPHome. 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 ESPHome 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 ESPHome MCP in LlamaIndex

Use `llama-index-tools-mcp` with `BasicMCPClient` pointing to your Vinkius endpoint. Convert the tools using `McpToolSpec` so your agent can call `get_entity_state` to populate its memory.

Yes, by indexing the output of `get_metrics` and `get_entity_state` over time. The agent searches this historical vector store to identify patterns in your hardware usage.

The agent uses the `get_entity_state` tool to verify the actual state of a device before running an action. This ensures it doesn't try to open a cover that is already open.

You can use `number_set` and `select_option` to adjust target temperatures and modes on your climate nodes. The agent decides on these values by retrieving context from your local environment documents.

Your local entity states and Prometheus metrics are processed entirely within your isolated Vinkius container. This MCP Server keeps your data local.

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