How to Use the ESPHome MCP in LangChain

Q: How do I connect my ESPHome devices to a LangChain agent?

Install langchain-mcp-adapters and use MultiServerMCPClient to connect to the Vinkius endpoint. Pass the tools from client.gettools() to your agent constructor so it can run actions like switchaction directly.

Run multi-step IoT automation chains with your LangChain agent directly invoking ESPHome devices.

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 LangChain

Create your Vinkius account to connect ESPHome to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain-linked IoT state adjustments with LangChain

`get_entity_state` reads the current status of your ESPHome sensors, letting your LangChain agent feed that data directly into the next step of an execution chain. The agent takes the raw ESPHome REST API response and decides whether to trigger another tool without needing manual glue code in LangChain. You build multi-step reasoning pipelines where the output of checking an ESPHome sensor feeds straight into `switch_action` or `light_action` inside LangChain. LangSmith traces the entire flow, showing you the exact latency and payload of every single ESPHome call.

Direct ESP32 state configuration via LangChain

`number_set` modifies numerical configurations on your ESP32 boards based on real-time decision trees in your LangChain pipeline. Your LangChain agent parses the incoming ESPHome telemetry, compares it against your target values, and sends the update. This removes the need to write custom REST wrappers or handle raw HTTP requests inside your LangChain chains. The MCP Server lets the agent execute `select_option` to change ESPHome device modes or `button_press` to trigger specific local automations.

Real-time telemetry monitoring loops

`get_metrics` extracts Prometheus format metrics directly from your ESPHome nodes to feed into your LangChain decision loops. The LangChain agent reads WiFi signal strength and CPU heap status to determine if an ESP32 node is healthy before executing commands. If the ESPHome metrics indicate a node is struggling, the LangChain chain can bypass sending a `fan_action` or `cover_action` to avoid overloading the micro-controller. You get full visibility into these decisions through your LangSmith tracing dashboard.

Setup guide

Set up ESPHome MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes ESPHome tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "esphome-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent ESPHome transactions"
    })
    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 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 LangChain

Install `langchain-mcp-adapters` and use `MultiServerMCPClient` to connect to the Vinkius endpoint. Pass the tools from `client.get_tools()` to your agent constructor so it can run actions like `switch_action` directly.

Yes, the agent can chain tools together in a single execution loop. For example, it can call `get_entity_state` to check a room's status, and then immediately call `cover_action` to close the blinds based on that result.

The MCP Server returns a standard error schema when a device is unreachable. Your LangChain agent receives this error as tool output, allowing it to retry or fail gracefully within your pipeline.

You configure tool access at the agent level by filtering the list returned by the server. Only pass specific tools like `light_action` or `fan_action` to the agent if you want to restrict its control.

The MCP Server only processes local entity states and device action payloads. Your physical sensor data and command history stay within the secure Vinkius sandbox and your local network.

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