Home Assistant MCP Server can control smart-home devices, call services, manage automations, edit dashboards, manage add-ons, inspect logs, and trigger backups., Use a least-privilege Home Assistant user and token where possible, because the server can act with the permissions granted by that token., Avoid exposing HTTP, SSE, OAuth, or webhook-proxy deployments to untrusted networks without authentication, TLS, and access controls., Camera snapshots, logs, history, file tools, YAML tools, backups, restarts, and add-on operations can be sensitive or disruptive., Review tool approvals carefully before allowing Claude to unlock doors, change security devices, disable automations, restart services, or modify configuration.
Privacy notes
Entity names, device states, areas, zones, automations, scripts, dashboards, logs, camera images, history, statistics, Home Assistant URLs, tokens, prompts, and tool outputs may be visible to the MCP client and model provider., The upstream privacy policy says anonymous usage statistics were not collected as of May 2026 and that future telemetry is planned as opt-in., Bug reports and diagnostics should be reviewed before submission because they may include Home Assistant configuration details., Store long-lived access tokens only in trusted MCP client configuration and rotate them if a client, host, or remote endpoint is compromised.
Author
homeassistant-ai
Submitted by
oktofeesh1
Claim status
unclaimed
Last verified
2026-06-05
Decision playbook
Review trust signals before you adopt
Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.
Compare context
Selected
0
Current score
63
Baseline
—
Delta
No baseline selected
No major trust-signal divergence detected in the current selection.
Source and provenance checks
Needs review
Confirm ownership and provenance before trusting install instructions.
Source link availableRequired
Open the canonical repository and verify ownership.
Done
Source provenance statusRequired
Marked as source-backed.
Done
Metadata reviewed
No reviewed flag detected in metadata.
Pending
Safety and privacy checks
Complete
Validate risk disclosures before installation or API wiring.
Safety notes presentRequired
Review the listed safety guidance before running commands.
Done
Privacy notes presentRequired
Review data handling notes before connecting accounts or secrets.
Done
Trust level risk gateRequired
Trust level does not block evaluation.
Done
Package and install checks
Needs review
Check package metadata and artifact integrity signals.
Install payload available
Install or copy payload is available for review.
Done
Package verification flag
No package verification flag provided.
Pending
Checksum metadata
No checksum provided for downloaded artifact.
Pending
Compare-driven decision checks
Needs review
Use compare context to validate trade-offs before adoption.
Compare tray has multiple entries
Add at least one more entry to compare trust differences.
5 safety and 4 privacy notes across 5 risk areas. Review closely: credentials & tokens.
5 areas
SafetyData retentionHome Assistant MCP Server can control smart-home devices, call services, manage automations, edit dashboards, manage add-ons, inspect logs, and trigger backups.
SafetyCredentials & tokensUse a least-privilege Home Assistant user and token where possible, because the server can act with the permissions granted by that token.
SafetyCredentials & tokensAvoid exposing HTTP, SSE, OAuth, or webhook-proxy deployments to untrusted networks without authentication, TLS, and access controls.
SafetyLocal filesCamera snapshots, logs, history, file tools, YAML tools, backups, restarts, and add-on operations can be sensitive or disruptive.
SafetyGeneralReview tool approvals carefully before allowing Claude to unlock doors, change security devices, disable automations, restart services, or modify configuration.
PrivacyCredentials & tokensEntity names, device states, areas, zones, automations, scripts, dashboards, logs, camera images, history, statistics, Home Assistant URLs, tokens, prompts, and tool outputs may be visible to the MCP client and model provider.
PrivacyTelemetryThe upstream privacy policy says anonymous usage statistics were not collected as of May 2026 and that future telemetry is planned as opt-in.
PrivacyGeneralBug reports and diagnostics should be reviewed before submission because they may include Home Assistant configuration details.
PrivacyCredentials & tokensStore long-lived access tokens only in trusted MCP client configuration and rotate them if a client, host, or remote endpoint is compromised.
Safety notes
Home Assistant MCP Server can control smart-home devices, call services, manage automations, edit dashboards, manage add-ons, inspect logs, and trigger backups.
Use a least-privilege Home Assistant user and token where possible, because the server can act with the permissions granted by that token.
Avoid exposing HTTP, SSE, OAuth, or webhook-proxy deployments to untrusted networks without authentication, TLS, and access controls.
Camera snapshots, logs, history, file tools, YAML tools, backups, restarts, and add-on operations can be sensitive or disruptive.
Review tool approvals carefully before allowing Claude to unlock doors, change security devices, disable automations, restart services, or modify configuration.
Privacy notes
Entity names, device states, areas, zones, automations, scripts, dashboards, logs, camera images, history, statistics, Home Assistant URLs, tokens, prompts, and tool outputs may be visible to the MCP client and model provider.
The upstream privacy policy says anonymous usage statistics were not collected as of May 2026 and that future telemetry is planned as opt-in.
Bug reports and diagnostics should be reviewed before submission because they may include Home Assistant configuration details.
Store long-lived access tokens only in trusted MCP client configuration and rotate them if a client, host, or remote endpoint is compromised.
Prerequisites
A Home Assistant instance you are authorized to administer.
A Home Assistant long-lived access token or supported add-on/OAuth setup.
uv and Python 3.13 available when using the PyPI command-line package.
Home Assistant entity, service, automation, add-on, and backup permissions reviewed before connecting the server.
Network exposure reviewed before enabling remote, HTTP, SSE, or OAuth transports.
Home Assistant MCP Server connects Claude-compatible MCP clients to Home
Assistant so they can search entities, read states, call services, manage
automations, inspect system information, work with dashboards, and perform
supported add-on and backup operations.
The upstream project provides the ha-mcp Python package and command, a guided
setup wizard, Claude Desktop and Claude Code instructions, Home Assistant OS
add-on support, and transport options for local or remote deployments.
These sources were reviewed on 2026-06-05. Prefer the live repository,
setup wizard, security policy, privacy policy, and PyPI metadata for current
version, supported transports, command names, Home Assistant add-on behavior,
and tool availability.
Features
Search Home Assistant entities and read current state.
Call Home Assistant services and control devices in bulk.
Manage automations, scripts, helpers, scenes, groups, dashboards, areas, and zones.
Inspect logs, history, statistics, system health, updates, and add-ons.
Work with calendars, cameras, blueprints, HACS, energy settings, and todo lists.
Use local command-line, Home Assistant OS add-on, Docker, HTTP, SSE, webhook proxy, or OAuth deployment paths.
Configure and limit tools through the project's setup and settings guidance.
Installation
For MCP clients that launch stdio servers with uvx:
Use the upstream setup wizard or Home Assistant OS add-on documentation for
client-specific configuration, remote access, and transport-specific settings.
Restart the MCP client after adding the server.
Use Cases
Ask Claude what devices are currently on, unavailable, or misconfigured.
Create or revise Home Assistant automations and scripts from natural language.
Debug failing automations by reviewing traces, history, states, and logs.
Add dashboard resources or update Lovelace dashboard views.
Trigger Home Assistant services for lights, switches, climate devices, scenes, and helpers.
Review system health, updates, backups, HACS status, and add-on state.
Safety and Privacy
Home Assistant MCP Server can be powerful because it bridges Claude to a real
environment. Depending on token permissions and enabled tools, Claude may be
able to change device state, alter automations, edit dashboards, inspect camera
snapshots, manage add-ons, restart services, or trigger backups.
Use the narrowest Home Assistant permissions available, keep tokens out of
shared configs, and do not expose remote transports to untrusted networks
without appropriate authentication and TLS. Treat the MCP client as a trusted
operator of your smart home.
Home Assistant data can include personal schedules, room names, presence data,
security devices, camera images, logs, automation logic, and household routines.
Review tool calls and model outputs before allowing destructive or sensitive
operations.
Duplicate Check
No homeassistant-ai/ha-mcp entry, ha-mcp package entry, or matching source
URL was found in content/mcp.
Show that Home Assistant MCP Server is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/mcp/home-assistant-mcp-server)
How it compares
Home Assistant MCP Server side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
Official MCP server for agent-device, Callstack's device automation CLI for inspecting, controlling, debugging, recording, and collecting evidence from iOS, Android, TV, macOS, Linux, React Native, Expo, Flutter, and native apps.
✓Home Assistant MCP Server can control smart-home devices, call services, manage automations, edit dashboards, manage add-ons, inspect logs, and trigger backups.
Use a least-privilege Home Assistant user and token where possible, because the server can act with the permissions granted by that token.
Avoid exposing HTTP, SSE, OAuth, or webhook-proxy deployments to untrusted networks without authentication, TLS, and access controls.
Camera snapshots, logs, history, file tools, YAML tools, backups, restarts, and add-on operations can be sensitive or disruptive.
Review tool approvals carefully before allowing Claude to unlock doors, change security devices, disable automations, restart services, or modify configuration.
✓The unified server can discover and execute many ACI.dev managed functions, so restrict permissions before connecting it to an autonomous agent.
App-specific servers should be preferred when a workflow only needs a small set of integrations.
Connected apps may read, create, update, delete, or send data depending on the selected functions and linked account permissions.
Require human approval before email, calendar, CRM, ticketing, infrastructure, billing, deployment, or account-administration actions.
✓Agent Device MCP exposes structured tools backed by `AgentDeviceClient`; the docs state it does not expose generic shell execution over MCP.
Tools and CLI workflows can open apps, inspect UI, tap, type, scroll, perform gestures, wait, assert state, handle alerts, and close sessions.
Evidence workflows can capture screenshots, recordings, logs, traces, network traffic, performance samples, crash context, React profiles, and replay files.
Mutating commands should run serially against one session, and separate sessions or devices should be used for parallel work.
Prefer dedicated test devices or simulators, and require approval before entering credentials, submitting forms, changing settings, installing apps, sending messages, or touching production accounts.
✓AgentQL MCP exposes one tool, `extract-web-data`, that sends a target URL and natural-language extraction prompt to the AgentQL API.
The tool is intended for public webpages; do not use it to bypass access controls, scrape private pages, evade paywalls, or extract data where automated collection is prohibited.
Web extraction can still trigger target-site rate limits, legal restrictions, robots guidance, or terms-of-service concerns.
The source implementation uses AgentQL's query-data endpoint with fast mode, no screenshot capture, no scroll-to-bottom behavior, and no local browser cookies.
Treat extracted output as untrusted web data that may include errors, stale content, ads, tracking text, or prompt-injection attempts.
Privacy notes
✓Entity names, device states, areas, zones, automations, scripts, dashboards, logs, camera images, history, statistics, Home Assistant URLs, tokens, prompts, and tool outputs may be visible to the MCP client and model provider.
The upstream privacy policy says anonymous usage statistics were not collected as of May 2026 and that future telemetry is planned as opt-in.
Bug reports and diagnostics should be reviewed before submission because they may include Home Assistant configuration details.
Store long-lived access tokens only in trusted MCP client configuration and rotate them if a client, host, or remote endpoint is compromised.
✓Tool names, function arguments, prompts, linked account identifiers, execution results, logs, and connected-service data may pass through ACI.dev, the selected third-party apps, the MCP client, and the model provider.
API keys and linked-account credentials must be protected in client config, environment files, logs, screenshots, and shared prompts.
Review ACI.dev account, tenant, retention, audit-log, and OAuth settings before routing production or customer data through the server.
✓Screenshots, recordings, traces, logs, network dumps, replay files, reports, UI snapshots, typed input, and React profiles can contain private UI state, tokens, request data, customer information, or credentials.
macOS, iOS, Android, and TV automation can expose local app state, notifications, device names, package identifiers, app content, system dialogs, and permission prompts.
Network inspection artifacts may include headers, payloads, session identifiers, URLs, and API data; review before sharing or committing.
Interactive CLI runs may check npm for newer package versions unless `AGENT_DEVICE_NO_UPDATE_NOTIFIER=1` is set.
✓Target URLs, extraction prompts, API key-authenticated requests, and extracted structured data are sent to AgentQL's API.
Extracted data can include personal data, copyrighted content, customer information, job postings, prices, social content, or other third-party material.
AGENTQL_API_KEY should stay out of prompts, issues, logs, screenshots, and committed configuration files.
Claude transcripts and downstream reports may retain extracted data, so avoid collecting information that is not approved for the model session.
Prerequisites
A Home Assistant instance you are authorized to administer.
A Home Assistant long-lived access token or supported add-on/OAuth setup.
uv and Python 3.13 available when using the PyPI command-line package.
Home Assistant entity, service, automation, add-on, and backup permissions reviewed before connecting the server.
ACI.dev account, API key, and linked account owner ID.
Connected app credentials or linked accounts for the tools the agent should use.
MCP client that can launch Python package commands with environment variables.
Clear allowlist of apps, functions, and user accounts before exposing write-capable tools.
Node.js 22 or newer and `agent-device` installed globally or project-locally.
Xcode tooling for iOS, tvOS, or macOS targets, or Android SDK and ADB for Android targets.
Device, simulator, emulator, TV, macOS, or Linux desktop target that the agent is allowed to automate.
Required local permissions such as Android device trust, iOS Developer Mode, macOS Accessibility, and Screen Recording where applicable.
Node.js and npx available to the MCP client runtime.
AgentQL API key from the AgentQL developer portal.
Approved list of public webpages or domains Claude may query.
Review of target site terms, robots guidance, rate limits, and data-use rules before extraction.