How to Use the Home Assistant MCP in CrewAI

Q: How do I assign Home Assistant tools to a CrewAI agent?

Pass your MCP Server URL directly into the agent's mcps list during initialization. This grants that specific agent access to tools like callhaservice while keeping other agents restricted.

Q: Can a CrewAI agent run complex Home Assistant templates?

Yes. The agent uses renderhatemplate to evaluate Jinja2 expressions directly on your local instance. This lets the crew process complex state logic without writing custom python code.

Run autonomous multi-agent crews to monitor and secure your home using CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Home Assistant MCP to CrewAI

Create your Vinkius account to connect Home Assistant 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 Home Assistant with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Home monitoring with CrewAI

This MCP Server exposes `list_entity_states` to let your specialized CrewAI agents monitor your entire home environment. One agent watches temperature sensors while another coordinates the HVAC system to keep things balanced. The agents share a common memory space, allowing them to collaborate on complex scenarios.

Event-driven team response

The `list_ha_events` tool lets your agent team understand exactly what events your home is tracking in real-time. When a specific trigger fires, the crew divides the response tasks based on their defined roles. A security agent runs `get_logbook_entries` to see who last accessed a door, while a notification agent alerts you.

Automated system health monitoring

The `get_ha_config` tool provides your crew with the exact hardware and integration configuration of your local setup. A dedicated system administrator agent analyzes this data to find inactive components. Checking for loaded integrations using `list_ha_components` ensures everything is running.

Setup guide

Set up Home Assistant 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 Home Assistant tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent Home Assistant 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="Home Assistant Analyst",
        goal="Access and analyze Home Assistant data via MCP.",
        backstory="Expert analyst with direct Home Assistant access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Home Assistant 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 Home Assistant. 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 Home Assistant 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 Home Assistant MCP in CrewAI

Pass your MCP Server URL directly into the agent's `mcps` list during initialization. This grants that specific agent access to tools like `call_ha_service` while keeping other agents restricted.

Yes. The agent uses `render_ha_template` to evaluate Jinja2 expressions directly on your local instance. This lets the crew process complex state logic without writing custom python code.

Yes, the crew runs locally or in your cloud environment and communicates with your home via secure HTTP. Use `get_api_status` to verify the network route is clear before starting a crew run.

Yes, you limit which tools an agent uses by configuring the `MCPServerHTTP` class with a tool filter. This prevents a research agent from executing actions outside its scope on your MCP setup.

No smart home logs or states are stored. All data queried via this connection is processed purely in-memory within an ephemeral sandbox and discarded immediately after the execution finishes.

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