Skip to main content
Glama
Home Assistant MCP Server

Home Assistant MCP Server

Official

List Dashboard Resources

ha_config_list_dashboard_resources
Read-onlyIdempotent

List Lovelace dashboard resources, including custom cards, themes, CSS and JS, with pagination and optional content or hash details for managing and verifying updates.

Instructions

List Lovelace dashboard resources (custom cards, themes, CSS/JS).

Returns one page of registered resources; total_count and has_more report the full set, and inline_count and by_type summarise every resource, not just this page. Each resource has a unique ID for update/delete operations. For inline resources (created with ha_config_set_dashboard_resource(content=...)), shows a preview of the content instead of the full encoded URL to save tokens. resource_mode is Core's lovelace resource mode; in 'yaml' mode resources cannot be created, updated or deleted through the API.

EXAMPLES:

  • Next page: ha_config_list_dashboard_resources(offset=100)

  • List with full content: ha_config_list_dashboard_resources(include_content=True)

  • Verify an edit by hash: ha_config_list_dashboard_resources(include_hash=True)

Home Assistant 2026.6+ exposes resource management in the UI by default; API access works regardless of UI availability.

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_config_list_dashboard_resources"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax resources to return per page
offsetNoNumber of resources to skip for pagination
include_hashNoAdd "_config_hash" (SHA-256 hex digest of the decoded UTF-8 content) to each inline resource, e.g. to verify an edit or to pass as config_hash without fetching the content.
include_contentNoInclude full decoded content for inline resources in the "_content" field. When False, a 150-char preview is shown instead. Rows past the per-response content budget carry '_content_truncated': True instead of '_content'; request a smaller page before copying content into an update.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv9.1.0
    • addedInput schema / properties / include_hash
      Added value: +{
      +  "default": false,
      +  "description": "Add \"_config_hash\" (SHA-256 hex digest of the decoded UTF-8 content) to each inline resource, e.g. to verify an edit or to pass as config_hash without fetching the content.",
      +  "type": "boolean"
      +}
  2. Changed3 schema fields changedv8.6.0
    • changedInput schema / properties / include_content / description
      Previous value: -"Include full decoded content for inline resources. Default False to save tokens (shows 150-char preview instead)."New value: +"Include full decoded content for inline resources in the \"_content\" field. When False, a 150-char preview is shown instead. Rows past the per-response content budget carry '_content_truncated': True instead of '_content'; request a smaller page before copying content into an update."
    • changedInput schema / properties / limit / description
      Previous value: -"Max resources to return per page (default: 100)"New value: +"Max resources to return per page"
    • changedInput schema / properties / offset / description
      Previous value: -"Number of resources to skip for pagination (default: 0)"New value: +"Number of resources to skip for pagination"
  3. First observedv7.14.2

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the readOnly/idempotent annotations, it discloses non-obvious behavior: page-level vs aggregate counts (total_count/has_more vs inline_count/by_type), a token-saving preview mode for inline resources, a per-response content budget that yields '_content_truncated', and the constraint that in 'yaml' resource_mode mutations are impossible via the API.

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

Conciseness4/5

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

The pagination/summary semantics are front-loaded and the examples are compact and actionable. The closing note about Home Assistant 2026.6+ UI availability is the least load-bearing sentence, though it does warn that UI availability and API availability differ.

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

Completeness5/5

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

For a read-only paginated list with a full output schema, the description covers everything an agent needs: paging semantics, when previews replace content, truncation signaling, ID availability for follow-up update/delete, and the yaml-mode restriction.

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?

Schema coverage is already 100%, so the base is 3; the description earns extra by tying parameters to intent — offset for next page, include_content for full content, include_hash for verifying an edit or passing config_hash without refetching. It doesn't add new syntax, but it maps each flag to a concrete workflow.

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?

The opening sentence gives a specific verb and resource ('List Lovelace dashboard resources') and scopes the content with examples ('custom cards, themes, CSS/JS'), which immediately separates it from siblings like ha_config_get_dashboard or ha_config_set_dashboard_resource.

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?

It supplies concrete usage contexts (paging with offset=100, include_content=True for full content, include_hash=True to verify an edit) and points at ha_config_set_dashboard_resource for the create path. The one gap is that no explicit 'do not use this to...' exclusion is stated, so the agent must infer that mutations belong to the set/delete siblings.

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