How to Use the ESPHome MCP in CrewAI

Q: Can I restrict which ESPHome tools a CrewAI agent can use?

Yes. You initialize MCPServerHTTP and use the toolfilter parameter. This lets you give one agent read-only access while another gets full control.

Deploy specialized CrewAI agents to monitor and control your ESPHome devices autonomously.

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 CrewAI

Create your Vinkius account to connect ESPHome to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Dedicated hardware monitoring agents via MCP Server

You assign the `get_entity_state` and `get_metrics` tools to a dedicated CrewAI watcher agent. This agent continuously polls your local network, building a running memory of normal operating conditions. When the watcher detects an anomaly in the `get_metrics` output, it escalates the issue to a response agent. The response agent parses the context and decides whether to intervene or just log the event.

Autonomous environmental control

By exposing `light_action` and `fan_action` through this MCP Server, your execution agent handles physical environment adjustments. It receives instructions from the analyzer agent and fires the exact HTTP requests needed to correct the room temperature. The agent uses `number_set` to fine-tune climate parameters based on external weather APIs. It acts without human input, adjusting blinds via `cover_action` to block direct sunlight during peak heat hours.

Coordinated security responses

A security-focused agent takes control of the `alarm_action` tool during a breach scenario. If a separate agent detects unauthorized access, the security agent arms the panel and triggers local sirens. The system sequences multiple hardware calls rapidly using `switch_action` to flash exterior lights. It simultaneously locks smart deadbolts via the web server API to secure the perimeter.

Setup guide

Set up ESPHome MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke ESPHome tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="ESPHome Analyst",
    goal="Access and analyze ESPHome data via MCP.",
    backstory="Expert analyst with direct ESPHome access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent ESPHome transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="ESPHome Analyst",
        goal="Access and analyze ESPHome data via MCP.",
        backstory="Expert analyst with direct ESPHome access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent ESPHome transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You add the endpoint URL directly into the mcps array parameter when defining your agent in Python.

Yes. You initialize MCPServerHTTP and use the tool_filter parameter. This lets you give one agent read-only access while another gets full control.

You configure your crew with a sequential execution process. The first agent runs get_entity_state, passes the result to the next agent, which then executes the required button_press.

The framework handles stdio, SSE, and Streamable HTTP natively. You just provide the URL and the client negotiates the connection automatically.

The server reads your entity IDs, MAC addresses, and current sensor states. Vinkius processes these requests in a sandboxed V8 isolate that wipes all memory the moment the Python script terminates the connection.

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