Home Assistant MCP integration for AI agents.
Connect AI agents to Home Assistant through 28 structured actions, including check config, execute script, delete automation config, and call service. Review…
- ACTION CONTRACTS
- 28
- AUTHENTICATION
- API key
- SOURCE STATUS
- Provider-backed
CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE
CAPABILITY PROFILE
What the Home Assistant integration exposes
The Home Assistant Agent App exposes 28 provider-backed actions for productivity work. Its current contract lets an authorized agent ask home assistant to validate its own configuration files and report errors and warnings. requires an admin access token, run a home assistant script sequence, which can chain several service calls, delays, and conditions in one request instead of one service call at a time, and delete one home assistant automation. requires an admin access token, and only covers entries stored in the home assistant ui-editable config; entries defined in other yaml files return not found. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.
A connection uses API key. Before execution, the agent can inspect the selected action, its required fields, declared scopes, and expected output contract. Provider credentials remain inside the Working Machines runtime; the calling agent receives the capability and its structured result, not the underlying secret.
For reliable operation, start with the narrowest action that satisfies the task, resolve stable provider identifiers before changing state, and validate the returned object or status after execution. Availability still depends on the connected Home Assistant account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real Home Assistant capabilities.
Showing 12 of 28 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
check_configREADAsk Home Assistant to validate its own configuration files and report errors and warnings. Requires an admin access token.
execute_scriptWRITERun a Home Assistant script sequence, which can chain several service calls, delays, and conditions in one request instead of one service call at a time.
INPUTS: sequence / variables
delete_automation_configHIGH IMPACTDelete one Home Assistant automation. Requires an admin access token, and only covers entries stored in the Home Assistant UI-editable config; entries defined in other YAML files return not found.
INPUTS: automationId
call_serviceREVIEWCall a Home Assistant service to control entities, such as light.turn_on or switch.turn_off.
INPUTS: domain / service / serviceData / returnResponse
delete_scene_configHIGH IMPACTDelete one Home Assistant scene. Requires an admin access token, and only covers entries stored in the Home Assistant UI-editable config; entries defined in other YAML files return not found.
INPUTS: sceneId
delete_script_configHIGH IMPACTDelete one Home Assistant script. Requires an admin access token, and only covers entries stored in the Home Assistant UI-editable config; entries defined in other YAML files return not found.
INPUTS: scriptKey
fire_eventREVIEWFire one Home Assistant event with optional event data.
INPUTS: eventType / eventData
get_automation_configREADFetch the stored configuration for one Home Assistant automation. Requires an admin access token, and only covers entries stored in the Home Assistant UI-editable config; entries defined in other YAML files return not found.
INPUTS: automationId
get_configREADFetch the Home Assistant instance configuration.
get_error_logREADFetch the Home Assistant error log for the current session as plain text. Home Assistant serves this only when the instance runs with file logging enabled, so it can report not found on an otherwise healthy instance.
get_historyREADFetch recorded state history for one or more Home Assistant entities over a time period, for answering questions about how a value changed.
INPUTS: entityIds / startTime / endTime / minimalResponse / noAttributes
get_logbookREADFetch the Home Assistant logbook: the human-readable timeline of what happened and what triggered it, for diagnosing why something changed.
INPUTS: startTime / endTime / entityIds / period / contextId
INPUT CONTRACTS
Know what the action needs before it runs.
execute_script
sequenceREQUIRED- The Home Assistant script steps to run, in the same format as a script's sequence.
variablesOPTIONAL- Optional variables made available to the script sequence.
delete_automation_config
automationIdREQUIRED- The automation id to delete.
call_service
domainREQUIRED- The Home Assistant service domain, for example light or switch.
serviceREQUIRED- The Home Assistant service name, for example turn_on or turn_off.
serviceDataOPTIONAL- The JSON service data sent directly to Home Assistant, such as entity_id or brightness.
returnResponseOPTIONAL- Whether to request service response data with the return_response query parameter.
delete_scene_config
sceneIdREQUIRED- The scene id to delete.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Check Config
Ask Home Assistant to validate its own configuration files and report errors and warnings. Requires an admin access token. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
check_configControl Execute Script
Run a Home Assistant script sequence, which can chain several service calls, delays, and conditions in one request instead of one service call at a time. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.
execute_scriptVerify with Get Automation Config
Fetch the stored configuration for one Home Assistant automation. Requires an admin access token, and only covers entries stored in the Home Assistant UI-editable config; entries defined in other YAML files return not found. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
get_automation_configSAFETY BOUNDARY
Operate Home Assistant with explicit limits
- Authorize Home Assistant with API key and grant only the provider access required by the selected actions.
- 4 actions are change-capable by name. Confirm the target identity and material parameters before allowing a write.
- Treat `delete_automation_config`, `delete_scene_config`, and `delete_script_config` as high-impact operations and require an explicit approval boundary.
- No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in Home Assistant rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the Home Assistant task completed successfully.
CONNECTION MODEL
API key
Home Assistant long-lived access token used with the Authorization: Bearer header. Create it from your Home Assistant user profile page.
Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.
- READ SIGNALS
- 17
- WRITE SIGNALS
- 1
- HIGH IMPACT
- 3
- REVIEW SIGNALS
- 7
EVIDENCE AND AVAILABILITY
Provider reference
Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by Home Assistant.