Skip to main content
Glama
Sign In
Home Assistant MCP Server

Home Assistant MCP Server

Official
by homeassistant-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

List Available Services

ha_list_services
Read-onlyIdempotent

Discover and list available Home Assistant services to call, with domain filtering, search, pagination, and detail control for targeted service discovery.

Instructions

List available Home Assistant services with optional pagination and detail control.

Discovers services/actions that can be called via ha_call_service.

EXAMPLES:

  • Light services with full parameter details: ha_list_services(domain="light", detail_level="full")

  • Search: ha_list_services(query="temperature")

  • Next page: ha_list_services(offset=50)

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "ha_list_services"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax services to return per page
queryNoSearch in service names and descriptions.
domainNoFilter by domain (e.g., 'light', 'switch', 'climate').
fieldsNoReturn only the specified top-level response keys to reduce response size (e.g. ["services"]). None = full response. Available keys: success, domains, services, total_count, count, offset, limit, has_more, next_offset, detail_level, filters_applied.
offsetNoNumber of services to skip for pagination
detail_levelNo'summary': name, description, domain, service, target and response when the service returns data. 'full': additionally include parameter field schemas.summary
service_fieldsNoProject each service record to only the specified keys. E.g. ["name", "description"] returns slim service records. None = full records. Unknown keys yield empty records. Available keys: name, description, domain, service, target (when present), response (when present), fields (full mode only).

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv9.1.2
    • changedInput schema / properties / detail_level / description
      Previous value: -"'summary': name, description, domain, service, and target when the service has one. 'full': additionally include parameter field schemas."New value: +"'summary': name, description, domain, service, target and response when the service returns data. 'full': additionally include parameter field schemas."
    • changedInput schema / properties / service_fields / description
      Previous value: -"Project each service record to only the specified keys. E.g. [\"name\", \"description\"] returns slim service records. None = full records. Unknown keys yield empty records. Available keys: name, description, domain, service, target (when present), fields (full mode only)."New value: +"Project each service record to only the specified keys. E.g. [\"name\", \"description\"] returns slim service records. None = full records. Unknown keys yield empty records. Available keys: name, description, domain, service, target (when present), response (when present), fields (full mode only)."
  2. Changed5 schema fields changedv8.6.0
    • changedInput schema / properties / detail_level / description
      Previous value: -"'summary': service name + description only (default). 'full': include parameter field schemas."New value: +"'summary': name, description, domain, service, and target when the service has one. 'full': additionally include parameter field schemas."
    • changedInput schema / properties / fields / description
      Previous value: -"Return only the specified top-level response keys to reduce response size (e.g. [\"services\"]). None = full response (default). Available keys: success, domains, services, total_count, count, offset, limit, has_more, next_offset, detail_level, filters_applied."New value: +"Return only the specified top-level response keys to reduce response size (e.g. [\"services\"]). None = full response. Available keys: success, domains, services, total_count, count, offset, limit, has_more, next_offset, detail_level, filters_applied."
    • changedInput schema / properties / limit / description
      Previous value: -"Max services to return per page (default: 50)"New value: +"Max services to return per page"
    • changedInput schema / properties / offset / description
      Previous value: -"Number of services to skip for pagination (default: 0)"New value: +"Number of services to skip for pagination"
    • changedInput schema / properties / service_fields / description
      Previous value: -"Project each service record to only the specified keys. E.g. [\"name\", \"description\"] returns slim service records. None = full records (default). Unknown keys yield empty records. Available keys: name, description, domain, service, fields (full mode only), target (full mode only)."New value: +"Project each service record to only the specified keys. E.g. [\"name\", \"description\"] returns slim service records. None = full records. Unknown keys yield empty records. Available keys: name, description, domain, service, target (when present), fields (full mode only)."
  3. First observedv7.14.2

TDQS

A4.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world, so safety is covered. The description adds context the annotations do not: that results are paged and that detail level controls whether parameter schemas are included, which affects response weight. It does not mention permissions, rate limits, or result ordering, so not a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

One lead sentence stating purpose and scope, one sentence stating the relationship to ha_call_service, then three compact labeled examples. No filler, and the most important framing is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values and paging metadata need not be described, and the annotations cover safety. The description covers filtering, paging, and detail levels adequately for a 7-parameter read tool. Minor gaps remain around default ordering and how to refine a search that returns too many results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema description coverage the baseline is 3, but the examples demonstrate non-obvious parameter interactions — domain with detail_level='full', query for search, offset for paging — which adds practical meaning beyond the field descriptions. It still does not explain how query matching works or how fields/service_fields interact in depth.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('List available Home Assistant services') plus the scope modifiers (pagination, detail control), and explicitly contrasts the role with ha_call_service by describing it as the discovery step. An agent can immediately distinguish discovery from invocation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The line 'Discovers services/actions that can be called via ha_call_service' gives clear routing context: use this to find a service, then call it elsewhere. The three examples cover filtering, search, and paging. No explicit when-not guidance (e.g., when to consult entities/domains instead) is given, so it falls short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools