Agent for interacting with Home Assistant REST API

These details have not been verified by PyPI

Development Status
- 4 - Beta
Environment
- Console
License
- OSI Approved :: MIT License
Operating System
- POSIX :: Linux
Programming Language
- Python :: 3

Project description

Home Assistant Agent

CLI or API | MCP | Agent

PyPI - Version MCP Server PyPI - Downloads GitHub Repo stars GitHub forks GitHub contributors PyPI - License GitHub GitHub last commit (by committer) GitHub pull requests GitHub closed pull requests GitHub issues GitHub top language GitHub language count GitHub repo size GitHub repo file count (file type) PyPI - Wheel PyPI - Implementation

Version: 1.0.1

Documentation — Installation, deployment, usage across the API, CLI, and MCP interfaces, the optional A2A agent server, and guidance for provisioning the Home Assistant platform are maintained in the official documentation.

Overview

Home Assistant Agent is a production-grade Agent and Model Context Protocol (MCP) server designed to interface directly with Agent for interacting with Home Assistant REST API.

Key Features

Consolidated Action-Routed MCP Tools: Minimizes token overhead and eliminates tool bloat in LLM contexts by grouping methods into optimized, togglable tool modules.
Enterprise-Grade Security: Comprehensive support for Eunomia policies, OIDC token delegation, and granular execution context tracking.
Integrated Graph Agent: Built-in Pydantic AI agent supporting the Agent Control Protocol (ACP) and standard Web interfaces (AG-UI).
Native Telemetry & Tracing: Out-of-the-box OpenTelemetry exports and native Langfuse tracing.

CLI or API

This agent wraps the Agent for interacting with Home Assistant REST API API. You can interact with it programmatically or via its integrated execution entrypoints.

Detailed instructions on how to use the underlying API wrappers, extended schema bindings, and developer SDK references are maintained in docs/index.md.

MCP

This server utilizes dynamic Action-Routed tools to optimize token overhead and maximize IDE compatibility.

Available MCP Tools

Auto-generated from the live MCP server — do not edit by hand.

Condensed action-routed tools (default — `MCP_TOOL_MODE=condensed`)

MCP Tool	Toggle Env Var	Description
`home_assistant_calendar`	`CALENDARTOOL`	Manage home assistant calendar operations.
`home_assistant_entities`	`ENTITIESTOOL`	Manage home assistant entities operations.
`home_assistant_events`	`EVENTSTOOL`	Manage home assistant events operations.
`home_assistant_history`	`HISTORYTOOL`	Manage home assistant history operations.
`home_assistant_logbook`	`LOGBOOKTOOL`	Manage home assistant logbook operations.
`home_assistant_panels`	`PANELSTOOL`	Manage home assistant panels operations.
`home_assistant_services`	`SERVICESTOOL`	Manage home assistant services operations.
`home_assistant_states`	`STATESTOOL`	Manage home assistant states operations.
`home_assistant_system`	`SYSTEMTOOL`	Manage home assistant system operations.
`home_assistant_voice`	`VOICETOOL`	Manage home assistant voice operations.

Verbose 1:1 API-mapped tools (`MCP_TOOL_MODE=verbose` or `both`)

42 per-operation tools — one per public API method (click to expand)

MCP Tool	Toggle Env Var	Description
`home_assistant_call_service`	`APITOOL`	Invoke the call_service operation.
`home_assistant_check_config`	`APITOOL`	Invoke the check_config operation.
`home_assistant_components`	`APITOOL`	Invoke the components operation.
`home_assistant_config`	`CONFIGTOOL`	Invoke the config operation.
`home_assistant_delete_state`	`APITOOL`	Invoke the delete_state operation.
`home_assistant_expose_entities`	`APITOOL`	Invoke the expose_entities operation.
`home_assistant_expose_or_unexpose_entities`	`APITOOL`	Invoke the expose_or_unexpose_entities operation.
`home_assistant_extract_from_target`	`APITOOL`	Invoke the extract_from_target operation.
`home_assistant_fire_event`	`APITOOL`	Invoke the fire_event operation.
`home_assistant_get_api_status`	`BASE_API_CLIENTTOOL`	Invoke the get_api_status operation.
`home_assistant_get_calendar_events`	`APITOOL`	Invoke the get_calendar_events operation.
`home_assistant_get_calendars`	`APITOOL`	Invoke the get_calendars operation.
`home_assistant_get_camera_proxy`	`APITOOL`	Invoke the get_camera_proxy operation.
`home_assistant_get_components`	`APITOOL`	Invoke the get_components operation.
`home_assistant_get_conditions_for_target`	`APITOOL`	Invoke the get_conditions_for_target operation.
`home_assistant_get_config`	`APITOOL`	Invoke the get_config operation.
`home_assistant_get_entity_registry_display`	`APITOOL`	Invoke the get_entity_registry_display operation.
`home_assistant_get_entity_registry_list_for_display`	`APITOOL`	Invoke the get_entity_registry_list_for_display operation.
`home_assistant_get_error_log`	`APITOOL`	Invoke the get_error_log operation.
`home_assistant_get_events`	`APITOOL`	Invoke the get_events operation.
`home_assistant_get_history`	`APITOOL`	Invoke the get_history operation.
`home_assistant_get_logbook`	`APITOOL`	Invoke the get_logbook operation.
`home_assistant_get_panels`	`APITOOL`	Invoke the get_panels operation.
`home_assistant_get_services`	`APITOOL`	Invoke the get_services operation.
`home_assistant_get_services_for_target`	`APITOOL`	Invoke the get_services_for_target operation.
`home_assistant_get_state`	`APITOOL`	Invoke the get_state operation.
`home_assistant_get_states`	`APITOOL`	Invoke the get_states operation.
`home_assistant_get_triggers_for_target`	`APITOOL`	Invoke the get_triggers_for_target operation.
`home_assistant_handle_intent`	`APITOOL`	Invoke the handle_intent operation.
`home_assistant_list_calendars`	`APITOOL`	Invoke the list_calendars operation.
`home_assistant_list_events`	`APITOOL`	Invoke the list_events operation.
`home_assistant_list_exposed_entities`	`APITOOL`	Invoke the list_exposed_entities operation.
`home_assistant_list_services`	`APITOOL`	Invoke the list_services operation.
`home_assistant_list_states`	`APITOOL`	Invoke the list_states operation.
`home_assistant_ping`	`APITOOL`	Invoke the ping operation.
`home_assistant_render_template`	`APITOOL`	Invoke the render_template operation.
`home_assistant_status`	`APITOOL`	Invoke the status operation.
`home_assistant_subscribe_events`	`APITOOL`	Invoke the subscribe_events operation.
`home_assistant_subscribe_trigger`	`APITOOL`	Invoke the subscribe_trigger operation.
`home_assistant_unsubscribe_events`	`APITOOL`	Invoke the unsubscribe_events operation.
`home_assistant_update_state`	`APITOOL`	Invoke the update_state operation.
`home_assistant_validate_config`	`APITOOL`	Invoke the validate_config operation.

10 action-routed tool(s) (default) · 42 verbose 1:1 tool(s). Each is enabled unless its <DOMAIN>TOOL toggle is set false; MCP_TOOL_MODE selects the surface (condensed default · verbose 1:1 · both). Auto-generated — do not edit.

Detailed tool schemas, parameter shapes, and validation constraints are preserved in docs/mcp.md.

Dynamic Tool Selection & Visibility

This MCP server supports dynamic toolset selection and visibility filtering at runtime. This allows you to restrict the set of exposed tools in order to prevent blowing up the LLM's context window.

You can configure tool filtering via multiple input channels:

CLI Arguments: Pass --tools or --toolsets (or their disabled counterparts --disabled-tools and --disabled-toolsets) during startup.
Environment Variables: Define standard environment variables:
- MCP_ENABLED_TOOLS / MCP_DISABLED_TOOLS
- MCP_ENABLED_TAGS / MCP_DISABLED_TAGS
HTTP SSE Request Headers: Pass custom headers during transport initialization:
- x-mcp-enabled-tools / x-mcp-disabled-tools
- x-mcp-enabled-tags / x-mcp-disabled-tags
HTTP SSE Request Query Parameters: Append query parameters directly to your transport connection URL:
- ?tools=tool1,tool2
- ?tags=tag1

When query strings or parameters are supplied, an LLM-free Knowledge Graph resolution layer (using DynamicToolOrchestrator) matches query intents against known tool tags, names, or descriptions, with safe fallback and automated 24-hour background cache refreshing.

MCP Configuration Examples

Install the slim [mcp] extra. All examples install home-assistant-agent[mcp] — the MCP-server extra that pulls only the FastMCP / FastAPI tooling (agent-utilities[mcp]). It deliberately excludes the heavy agent runtime (pydantic-ai, the epistemic-graph engine, dspy, llama-index), so uvx / container installs are far smaller. Use the full [agent] extra only when you need the integrated Pydantic AI agent.

stdio Transport (local IDEs — Cursor, Claude Desktop, VS Code)

{
  "mcpServers": {
    "home-assistant-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "home-assistant-agent[mcp]",
        "home-assistant-mcp"
      ],
      "env": {
        "MCP_TOOL_MODE": "condensed",
        "CALENDARTOOL": "True",
        "CONFIGTOOL": "True",
        "ENTITIESTOOL": "True",
        "EVENTSTOOL": "True",
        "HISTORYTOOL": "True",
        "HOME_ASSISTANT_AGENT_VERIFY": "True",
        "HOME_ASSISTANT_TOKEN": "your_long_lived_access_token_here",
        "HOME_ASSISTANT_URL": "http://localhost:8123",
        "LOGBOOKTOOL": "True",
        "PANELSTOOL": "True",
        "SERVICESTOOL": "True",
        "STATESTOOL": "True",
        "SYSTEMTOOL": "True",
        "VOICETOOL": "True"
      }
    }
  }
}

Streamable-HTTP Transport (networked / production)

{
  "mcpServers": {
    "home-assistant-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "home-assistant-agent[mcp]",
        "home-assistant-mcp",
        "--transport",
        "streamable-http",
        "--port",
        "8000"
      ],
      "env": {
        "TRANSPORT": "streamable-http",
        "HOST": "0.0.0.0",
        "PORT": "8000",
        "MCP_TOOL_MODE": "condensed",
        "CALENDARTOOL": "True",
        "CONFIGTOOL": "True",
        "ENTITIESTOOL": "True",
        "EVENTSTOOL": "True",
        "HISTORYTOOL": "True",
        "HOME_ASSISTANT_AGENT_VERIFY": "True",
        "HOME_ASSISTANT_TOKEN": "your_long_lived_access_token_here",
        "HOME_ASSISTANT_URL": "http://localhost:8123",
        "LOGBOOKTOOL": "True",
        "PANELSTOOL": "True",
        "SERVICESTOOL": "True",
        "STATESTOOL": "True",
        "SYSTEMTOOL": "True",
        "VOICETOOL": "True"
      }
    }
  }
}

Alternatively, connect to a pre-deployed Streamable-HTTP instance by url:

{
  "mcpServers": {
    "home-assistant-mcp": {
      "url": "http://localhost:8000/home-assistant-mcp/mcp"
    }
  }
}

Deploying the Streamable-HTTP server via Docker:

docker run -d \
  --name home-assistant-mcp-mcp \
  -p 8000:8000 \
  -e TRANSPORT=streamable-http \
  -e HOST=0.0.0.0 \
  -e PORT=8000 \
  -e MCP_TOOL_MODE=condensed \
  -e CALENDARTOOL=True \
  -e CONFIGTOOL=True \
  -e ENTITIESTOOL=True \
  -e EVENTSTOOL=True \
  -e HISTORYTOOL=True \
  -e HOME_ASSISTANT_AGENT_VERIFY=True \
  -e HOME_ASSISTANT_TOKEN=your_long_lived_access_token_here \
  -e HOME_ASSISTANT_URL=http://localhost:8123 \
  -e LOGBOOKTOOL=True \
  -e PANELSTOOL=True \
  -e SERVICESTOOL=True \
  -e STATESTOOL=True \
  -e SYSTEMTOOL=True \
  -e VOICETOOL=True \
  knucklessg1/home-assistant-agent:mcp

Auto-generated from the code-read env surface (MCP_TOOL_MODE + package vars) — do not edit.

Additional Deployment Options

home-assistant-agent can also run as a local container (Docker / Podman / uv) or be consumed from a remote deployment. The Deployment guide has full, copy-paste mcp_config.json for all four transports — stdio, streamable-http, local container / uv, and remote URL:

Local container / uv — launch the server from mcp_config.json via uvx, docker run, or podman run, or point at a local streamable-http container by url.
Remote URL — connect to a server deployed behind Caddy at http://home-assistant-mcp.arpa/mcp using the "url" key.

Agent

This repository features a fully integrated Pydantic AI Graph Agent. It communicates over the Agent Control Protocol (ACP) and interacts seamlessly with the Agent Web UI (AG-UI) and Terminal interface.

Running the Agent CLI

To start the interactive command-line agent:

# Set credentials
export HOME_ASSISTANT_URL="http://localhost:8123"
export HOME_ASSISTANT_TOKEN="your_token_here"
export HOME_ASSISTANT_AGENT_VERIFY="True"

# Run the agent server
home-assistant-agent --provider openai --model-id gpt-4o

Docker Compose Orchestration

The following docker/agent.compose.yml configures the Agent, Web UI, and Terminal Interface together:

version: '3.8'

services:
  home-assistant-agent-mcp:
    image: knucklessg1/home-assistant-agent:mcp
    container_name: home-assistant-agent-mcp
    hostname: home-assistant-agent-mcp
    restart: always
    env_file:
      - ../.env
    environment:
      - PYTHONUNBUFFERED=1
      - HOST=0.0.0.0
      - PORT=8000
      - TRANSPORT=streamable-http
    ports:
      - "8000:8000"
    healthcheck:
      test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:8000/health')"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 10s
    logging:
      driver: json-file
      options:
        max-size: "10m"
        max-file: "3"

  home-assistant-agent-agent:
    image: knucklessg1/home-assistant-agent:latest
    container_name: home-assistant-agent-agent
    hostname: home-assistant-agent-agent
    restart: always
    depends_on:
      - home-assistant-agent-mcp
    env_file:
      - ../.env
    command: [ "home-assistant-agent" ]
    environment:
      - PYTHONUNBUFFERED=1
      - HOST=0.0.0.0
      - PORT=9004
      - MCP_URL=http://home-assistant-agent-mcp:8000/mcp
      - PROVIDER=${PROVIDER:-openai}
      - MODEL_ID=${MODEL_ID:-gpt-4o}
      - ENABLE_WEB_UI=True
      - ENABLE_OTEL=True
    ports:
      - "9004:9004"
    healthcheck:
      test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:9004/health')"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 10s
    logging:
      driver: json-file
      options:
        max-size: "10m"
        max-file: "3"

Detailed graph node architecture explanations, custom skill configurations, and agentic trace guides are available in docs/agent.md.

Environment Variables

Package environment variables

Variable	Example	Description
`HOME_ASSISTANT_URL`	`http://localhost:8123`	1. HOME_ASSISTANT_URL: The base URL of your Home Assistant instance.
`HOME_ASSISTANT_TOKEN`	`your_long_lived_access_token_here`	2. HOME_ASSISTANT_TOKEN: Long-Lived Access Token generated from Home Assistant profile.
`HOME_ASSISTANT_AGENT_VERIFY`	`True`	3. HOME_ASSISTANT_AGENT_VERIFY: Toggle SSL certificate verification (True/False).
`HOME_ASSISTANT_SSL_VERIFY`	`True`	3b. HOME_ASSISTANT_SSL_VERIFY: Preferred SSL verification toggle; overrides HOME_ASSISTANT_AGENT_VERIFY when set (True/False).
`DEFAULT_AGENT_NAME`	`HomeAssistantAgent`	4. DEFAULT_AGENT_NAME: The default name/display identifier for this agent.
`AGENT_DESCRIPTION`	`Expert assistant for interacting with and managing Home Assistant smart home devices.`	5. AGENT_DESCRIPTION: Brief description of the agent's responsibilities.
`AGENT_SYSTEM_PROMPT`	`You are a helpful, secure home automation AI assistant. You can control home assistant lights, switches, media players, calendars, and query historical data.`	6. AGENT_SYSTEM_PROMPT: Core system prompt directing the agent's behavior and traits.
`CONFIGTOOL`	`True`	7. CONFIGTOOL: Enable config management tool.
`STATESTOOL`	`True`	8. STATESTOOL: Enable state inspection and modification tool.
`SERVICESTOOL`	`True`	9. SERVICESTOOL: Enable service call tool.
`EVENTSTOOL`	`True`	10. EVENTSTOOL: Enable event monitoring and subscription tool.
`HISTORYTOOL`	`True`	11. HISTORYTOOL: Enable historical state query tool.
`LOGBOOKTOOL`	`True`	12. LOGBOOKTOOL: Enable logbook and error log query tool.
`CALENDARTOOL`	`True`	13. CALENDARTOOL: Enable calendar schedule querying tool.
`PANELSTOOL`	`True`	14. PANELSTOOL: Enable HA custom panels list tool.
`VOICETOOL`	`True`	15. VOICETOOL: Enable voice entity exposition and settings tool.
`ENTITIESTOOL`	`True`	16. ENTITIESTOOL: Enable entity registry lookup and display tool.
`SYSTEMTOOL`	`True`	17. SYSTEMTOOL: Enable templates, intents, and system health tools.
`HOST`	`0.0.0.0`
`PORT`	`8000`
`TRANSPORT`	`stdio`	Options: stdio, streamable-http, sse
`ENABLE_OTEL`	`True`
`EUNOMIA_TYPE`	`none`	Options: none, embedded, remote
`EUNOMIA_POLICY_FILE`	`mcp_policies.json`

Inherited agent-utilities variables (apply to every connector)

Variable	Example	Description
`MCP_TOOL_MODE`	`condensed`	Tool surface: `condensed`
`MCP_ENABLED_TOOLS`	—	Comma-separated tool allow-list
`MCP_DISABLED_TOOLS`	—	Comma-separated tool deny-list
`MCP_ENABLED_TAGS`	—	Comma-separated tag allow-list
`MCP_DISABLED_TAGS`	—	Comma-separated tag deny-list
`EUNOMIA_REMOTE_URL`	—	Remote Eunomia authorization server URL
`OTEL_EXPORTER_OTLP_ENDPOINT`	—	OTLP collector endpoint
`MCP_CLIENT_AUTH`	—	Outbound MCP auth (`oidc-client-credentials` for fleet calls)
`OIDC_CLIENT_ID`	—	OIDC client id (service-account auth)
`OIDC_CLIENT_SECRET`	—	OIDC client secret (service-account auth)
`DEBUG`	`False`	Verbose logging
`PYTHONUNBUFFERED`	`1`	Unbuffered stdout (recommended in containers)
`MCP_URL`	`http://localhost:8000/mcp`	URL of the MCP server the agent connects to
`PROVIDER`	`openai`	LLM provider for the agent
`MODEL_ID`	`gpt-4o`	Model id for the agent
`ENABLE_WEB_UI`	`True`	Serve the AG-UI web interface

24 package + 16 inherited variable(s). Auto-generated from .env.example + the shared agent-utilities set — do not edit.

Every variable the server reads, grouped by purpose.

Connection & Credentials (Home Assistant)

Variable	Description	Default
`HOME_ASSISTANT_URL`	Base URL of the Home Assistant instance	`http://localhost:8123`
`HOME_ASSISTANT_TOKEN`	Long-Lived Access Token generated in Home Assistant	—
`HOME_ASSISTANT_AGENT_VERIFY`	Toggle SSL certificate verification (`True`/`False`)	`True`

MCP server / transport

Variable	Description	Default
`TRANSPORT`	`stdio`, `streamable-http`, or `sse`	`stdio`
`HOST`	Bind host (HTTP transports)	`0.0.0.0`
`PORT`	Bind port (HTTP transports)	`8000`
`MCP_TOOL_MODE`	Tool surface: `condensed`, `verbose`, or `both`	`condensed`
`MCP_ENABLED_TOOLS` / `MCP_DISABLED_TOOLS`	Comma-separated tool allow/deny list	—
`MCP_ENABLED_TAGS` / `MCP_DISABLED_TAGS`	Comma-separated tag allow/deny list	—
`PYTHONUNBUFFERED`	Unbuffered stdout (recommended in containers)	`1`

Agent runtime (full `[agent]` runtime only)

Variable	Description	Default
`DEFAULT_AGENT_NAME`	Default name/display identifier for the agent	`HomeAssistantAgent`
`AGENT_DESCRIPTION`	Description of the agent's smart home duties	built-in
`AGENT_SYSTEM_PROMPT`	Core Pydantic AI system prompt	built-in
`MCP_URL`	URL of the MCP server the agent connects to	`http://localhost:8000/mcp`
`PROVIDER`	LLM provider (e.g. `openai`)	`openai`
`MODEL_ID`	Model id (e.g. `gpt-4o`)	`gpt-4o`
`ENABLE_WEB_UI`	Serve the AG-UI web interface	`True`

Telemetry & governance

Variable	Description	Default
`ENABLE_OTEL`	Enable OpenTelemetry export	`True`
`OTEL_EXPORTER_OTLP_ENDPOINT`	OTLP collector endpoint	—
`OTEL_EXPORTER_OTLP_PUBLIC_KEY` / `OTEL_EXPORTER_OTLP_SECRET_KEY`	OTLP auth keys	—
`OTEL_EXPORTER_OTLP_PROTOCOL`	OTLP protocol (e.g. `http/protobuf`)	—
`EUNOMIA_TYPE`	Authorization mode: `none`, `embedded`, `remote`	`none`
`EUNOMIA_POLICY_FILE`	Embedded policy file	`mcp_policies.json`
`EUNOMIA_REMOTE_URL`	Remote Eunomia server URL	—

Tool toggles

Each action-routed tool can be disabled individually via its toggle env var (set to false): CONFIGTOOL, STATESTOOL, SERVICESTOOL, EVENTSTOOL, HISTORYTOOL, LOGBOOKTOOL, CALENDARTOOL, PANELSTOOL, VOICETOOL, ENTITIESTOOL, SYSTEMTOOL. The full list is in the Available MCP Tools table above.

See .env.example for a copy-paste starting point.

Security & Governance

Built directly upon the enterprise-ready agent-utilities core, standard security parameters are fully supported:

Access Control & Policy Enforcement

Eunomia Policies: Fine-grained, policy-driven tool authorization. Supports none, local embedded (mcp_policies.json), or centralized remote modes.
OIDC Token Delegation: Compliant with RFC 8693 token exchange for flowing authenticating user credentials from Web UI / ACP → Agent → MCP.
Scoped Credentials: Execution context runs restricted to the specific caller identity.

Runtime Security Grid

Feature	Functionality	Enablement
Tool Guard	Sensitivity inspection with human-in-the-loop validation	Enabled by default
Prompt Injection Defense	Input scanning, repetition monitoring, and recursive loop blocks	Enabled by default
Context Safety Guard	Stuck-loop detectors and contextual overflow preemptive alerts	Enabled by default

Installation

Pick the extra that matches what you want to run:

Extra	Installs	Use when
`home-assistant-agent[mcp]`	Slim MCP server only (`agent-utilities[mcp]` — FastMCP/FastAPI)	You only run the MCP server (smallest install / image)
`home-assistant-agent[agent]`	Full agent runtime (`agent-utilities[agent,logfire]` — Pydantic AI + the epistemic-graph engine)	You run the integrated agent
`home-assistant-agent[all]`	Everything (`mcp` + `agent` + `logfire`)	Development / both surfaces

# MCP server only (recommended for tool hosting — slim deps)
uv pip install "home-assistant-agent[mcp]"

# Full agent runtime (Pydantic AI + epistemic-graph engine)
uv pip install "home-assistant-agent[agent]"

# Everything (development)
uv pip install "home-assistant-agent[all]"      # or: python -m pip install "home-assistant-agent[all]"

Container images (`:mcp` vs `:agent`)

One multi-stage docker/Dockerfile builds two right-sized images, selected by --target:

Image tag	Build target	Contents	Entrypoint
`knucklessg1/home-assistant-agent:mcp`	`--target mcp`	`home-assistant-agent[mcp]` — slim, no engine/`pydantic-ai`/`dspy`/`llama-index`/`tree-sitter`	`home-assistant-mcp`
`knucklessg1/home-assistant-agent:latest`	`--target agent` (default)	`home-assistant-agent[agent]` — full agent runtime + epistemic-graph engine	`home-assistant-agent`

docker build --target mcp   -t knucklessg1/home-assistant-agent:mcp    docker/   # slim MCP server
docker build --target agent -t knucklessg1/home-assistant-agent:latest docker/   # full agent

docker/mcp.compose.yml runs the slim :mcp server; docker/agent.compose.yml runs the agent (:latest) with a co-located :mcp sidecar.

Knowledge-graph database (`epistemic-graph`)

The full agent ([agent] / :latest) embeds the epistemic-graph engine (pulled in transitively via agent-utilities[agent]). For production — or to share one knowledge graph across multiple agents — run epistemic-graph as its own database container and point the agent at it instead of embedding it. Deployment recipes (single-node + Raft HA), connection config, and the full database architecture (with diagrams) are documented in the epistemic-graph deployment guide. The slim [mcp] server does not require the database.

Documentation

The complete documentation is published as the official documentation site and is the recommended reference for installation, deployment, and day-to-day operation.

Page	Contents
Installation	pip, source, extras, prebuilt Docker image
Deployment	run the MCP server, the agent server, Compose, Caddy + Technitium, env config
Usage	the MCP tools, the `HomeAssistantApi` client, the CLI
Backing Platform	deploy Home Assistant with Docker
Overview	architecture, tool surface, ecosystem role
Concepts	concept registry (`CONCEPT:HASS-*`)

AGENTS.md is the canonical contributor/agent guidance.

Repository Owners

GitHub followers GitHub User's stars

Contribute

Contributions are welcome! Please ensure code quality by executing local checks before submitting pull requests:

Format code using ruff format .
Lint code using ruff check .
Validate type-safety with mypy .
Execute test suites using pytest

Deploy with `agent-os-genesis`

This package can be provisioned for you — skill-guided — by the agent-os-genesis universal skill (its single-package deploy mode): it picks your install method, seeds secrets to OpenBao/Vault (or .env), trusts your enterprise CA, registers the MCP server, and verifies it — the same machinery that stands up the whole Agent OS, narrowed to just this package. Ask your agent to "deploy home-assistant-agent with agent-os-genesis".

Install mode	Command
Bare-metal, prod (PyPI)	`uvx home-assistant-mcp` · or `uv tool install home-assistant-agent`
Bare-metal, dev (editable)	`uv pip install -e ".[all]"` · or `pip install -e ".[all]"`
Container, prod	deploy `knucklessg1/home-assistant-agent:latest` via docker-compose / swarm / podman / podman-compose / kubernetes
Container, dev (editable)	deploy `docker/compose.dev.yml` (source-mounted at `/src`; edits live on restart)

Secrets are read-existing + seeded via vault_sync — you are only prompted for what's missing.

Project details

These details have not been verified by PyPI

Development Status
- 4 - Beta
Environment
- Console
License
- OSI Approved :: MIT License
Operating System
- POSIX :: Linux
Programming Language
- Python :: 3

Release history Release notifications | RSS feed

This version

1.0.1

Jul 2, 2026

0.34.0

Jun 17, 2026

0.32.0

Jun 13, 2026

0.31.0

Jun 13, 2026

0.30.0

Jun 10, 2026

0.29.0

Jun 6, 2026

0.27.0

Jun 4, 2026

0.25.0

Jun 1, 2026

0.24.2

May 31, 2026

0.24.0

May 31, 2026

0.22.0

May 29, 2026

0.20.0

May 29, 2026

0.15.0

May 22, 2026

0.12.1

May 21, 2026

0.12.0

May 18, 2026

0.11.0

May 11, 2026

0.10.0

May 9, 2026

0.9.0

May 8, 2026

0.8.1

May 6, 2026

0.3.0

Apr 30, 2026

0.2.3

Apr 30, 2026

0.2.1

Apr 17, 2026

0.2.0

Apr 10, 2026

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

home_assistant_agent-1.0.1.tar.gz (46.1 kB view details)

Uploaded Jul 2, 2026 Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

home_assistant_agent-1.0.1-py3-none-any.whl (53.0 kB view details)

Uploaded Jul 2, 2026 Python 3

File details

Details for the file home_assistant_agent-1.0.1.tar.gz.

File metadata

Download URL: home_assistant_agent-1.0.1.tar.gz
Upload date: Jul 2, 2026
Size: 46.1 kB
Tags: Source
Uploaded using Trusted Publishing? No
Uploaded via: twine/6.2.0 CPython/3.14.4

File hashes

Hashes for home_assistant_agent-1.0.1.tar.gz
Algorithm	Hash digest
SHA256	`c9b5327800b2df8e2117743ada5875756efd8f01d15ce78cc1ce960f8c2e861a`
MD5	`b800c4d2074454877c5fb49b543933cf`
BLAKE2b-256	`c7fc353ec87d62100dbd48374f3a863bcb5e8410458e9af18fad1b3eeb642c54`

See more details on using hashes here.

File details

Details for the file home_assistant_agent-1.0.1-py3-none-any.whl.

File metadata

Download URL: home_assistant_agent-1.0.1-py3-none-any.whl
Upload date: Jul 2, 2026
Size: 53.0 kB
Tags: Python 3
Uploaded using Trusted Publishing? No
Uploaded via: twine/6.2.0 CPython/3.14.4

File hashes

Hashes for home_assistant_agent-1.0.1-py3-none-any.whl
Algorithm	Hash digest
SHA256	`87f9bf6dac4142f4fca9d6cbbbf2c34b6f0e196cacfe030b2866dcee51826d6f`
MD5	`7e9c0da472fefed12ce2f4f4f896e3e6`
BLAKE2b-256	`3a79ba93f32c9b265dd638848c3bb267bdc69e32b2b038212276a888fa790e04`

See more details on using hashes here.

home-assistant-agent 1.0.1

Navigation

Verified details

Maintainers

Unverified details

Meta

Classifiers

Project description

Home Assistant Agent

CLI or API | MCP | Agent

Overview

Key Features

CLI or API

MCP

Available MCP Tools

Condensed action-routed tools (default — MCP_TOOL_MODE=condensed)

Verbose 1:1 API-mapped tools (MCP_TOOL_MODE=verbose or both)

Dynamic Tool Selection & Visibility

MCP Configuration Examples

stdio Transport (local IDEs — Cursor, Claude Desktop, VS Code)

Streamable-HTTP Transport (networked / production)

Additional Deployment Options

Agent

Running the Agent CLI

Docker Compose Orchestration

Environment Variables

Package environment variables

Inherited agent-utilities variables (apply to every connector)

Connection & Credentials (Home Assistant)

MCP server / transport

Agent runtime (full [agent] runtime only)

Telemetry & governance

Tool toggles

Security & Governance

Access Control & Policy Enforcement

Runtime Security Grid

Installation

Container images (:mcp vs :agent)

Knowledge-graph database (epistemic-graph)

Documentation

Repository Owners

Contribute

Deploy with agent-os-genesis

Project details

Verified details

Maintainers

Unverified details

Meta

Classifiers

Release history Release notifications | RSS feed

Download files

Source Distribution

Built Distribution

File details

File metadata

File hashes

File details

File metadata

File hashes

Condensed action-routed tools (default — `MCP_TOOL_MODE=condensed`)

Verbose 1:1 API-mapped tools (`MCP_TOOL_MODE=verbose` or `both`)

Agent runtime (full `[agent]` runtime only)

Container images (`:mcp` vs `:agent`)

Knowledge-graph database (`epistemic-graph`)

Deploy with `agent-os-genesis`