How to Use the Home Assistant MCP in LlamaIndex

Q: How do I load Home Assistant tools into LlamaIndex?

Install llama-index-tools-mcp and instantiate a BasicMCPClient pointing to your local URL. Wrap it in McpToolSpec and call await mcptoolspec.totoollistasync() to feed the functions into your agent.

Q: Can LlamaIndex trigger Home Assistant scripts?

Yes, assuming you give it permission. The callhaservice tool handles execution, but you can use the allowedtools filter to restrict the agent to read-only operations if preferred.

Q: Does LlamaIndex index my Home Assistant calendars?

Only if you instruct it to call getcalendarevents and embed the results. The framework treats your local schedules as just another data source to vectorize and query.

Q: How do I fix context window limits with large smart homes?

Use this MCP server to call getentitystate to target specific devices instead of dumping the entire network state at once. Semantic search allows the agent to find the right entity ID first, then fetch only the relevant data.

Q: What happens to my Home Assistant location data?

GPS coordinates pulled via gethaconfig stay within your designated LlamaIndex vector store. The server runs in a V8 Isolate Sandbox, ensuring memory clears completely between sessions. Your physical address never touches unauthorized third-party endpoints.

Index your physical environment by connecting Home Assistant to LlamaIndex via this MCP Server.

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 LlamaIndex

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build RAG Apps on Home Assistant Data

`list_entity_states` dumps your entire physical device footprint into a format ready for vectorization. LlamaIndex ingests this raw array of sensors, locks, and climate data to build a searchable knowledge base of your house. When you ask if the front door is secure, the engine queries the index instead of guessing. `get_entity_history` provides the temporal depth needed for accurate retrieval. You can embed weeks of temperature readings into your vector store. The resulting application answers complex queries about energy usage patterns using hard data pulled directly from your local network.

Semantic Search for MCP Server Tools

`list_ha_components` exposes every active integration currently running on your local hardware. LlamaIndex reads this list and maps out the available capabilities of your smart home. If a user asks about media players, the system already knows if the Sonos integration is active. `list_available_services` tells the agent exactly what actions are possible across all domains. The engine embeds these service definitions so it knows the difference between toggling a switch and setting a precise HVAC temperature. You get highly accurate tool selection based on semantic matching.

Query Physical Events

`get_logbook_entries` feeds a continuous stream of physical events into your RAG pipeline. The system indexes motion sensor triggers, door openings, and light switches as they happen. You can search your home's recent history just like you search a document database. `get_ha_config` pulls your base installation parameters for context. If an automation fails, LlamaIndex cross-references the error with your timezone, elevation, and unit system settings. It grounds every troubleshooting answer in your actual configuration.

Setup guide

Set up Home Assistant 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 Home Assistant 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 Home Assistant tools.",
)
response = await agent.run("List recent Home Assistant 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 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 LlamaIndex

Install `llama-index-tools-mcp` and instantiate a `BasicMCPClient` pointing to your local URL. Wrap it in `McpToolSpec` and call `await mcp_tool_spec.to_tool_list_async()` to feed the functions into your agent.

Yes, assuming you give it permission. The `call_ha_service` tool handles execution, but you can use the `allowed_tools` filter to restrict the agent to read-only operations if preferred.

Only if you instruct it to call `get_calendar_events` and embed the results. The framework treats your local schedules as just another data source to vectorize and query.

Use this MCP server to call `get_entity_state` to target specific devices instead of dumping the entire network state at once. Semantic search allows the agent to find the right entity ID first, then fetch only the relevant data.

GPS coordinates pulled via `get_ha_config` stay within your designated LlamaIndex vector store. The server runs in a V8 Isolate Sandbox, ensuring memory clears completely between sessions. Your physical address never touches unauthorized third-party endpoints.

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