Get Dashboard

Get dashboard info - list all dashboards, get config, or search for cards.

MODE 1 — List: list_only=True Lists every dashboard's metadata (url_path, title, icon), storage and YAML alike (metadata only — bodies are never included here).

MODE 2 — Search: any of entity_id / card_type / heading provided Finds cards, badges, and header cards matching the criteria, including cards nested inside stacks, grids, conditional cards, button-card custom_fields, and state-switch states. Each match carries a python_path and a jq_path that locate the card for nested as well as top-level cards. The python_path is a Python subscript chain to be appended after config — e.g. python_transform=f'config{m["python_path"]}["icon"] = "mdi:x"' (it is NOT valid on its own without the config prefix). jq_path is the same location in jq dot-notation. Multiple criteria are AND-ed. Always fetches fresh config (force=True). Search covers cards/card/custom_fields/states containers up to a depth bound; if the dashboard carries a non-traversed child-bearing shape (e.g. picture-elements elements), the result carries a warnings entry naming where, so its hidden content is not mistaken for absent. Strategy dashboards are not searchable (no explicit cards).

MODE 3 — Get: Active when list_only=False and no search parameters are provided. Returns the full Lovelace dashboard config, defaulting to the main dashboard if url_path is omitted. Pass view_path=<views[].path> to return ONLY that view: the response then carries view + view_index instead of config, keeping the payload small on multi-view dashboards. config_hash still covers the FULL config, so a follow-up ha_config_set_dashboard(python_transform=...) addressing config['views'][view_index] validates unchanged. An unknown view_path errors and lists the available view paths.

MODE 4 — Search all: mode="search" with query= Answers "which dashboards contain this entity/card" by walking every storage-mode dashboard's views/cards/sections for the query substring. Each match names the url_path, view, card_path, card_type, and the matched field/value. Takes precedence over the other modes (list_only / entity_id / card_type / heading are ignored when mode="search"). YAML-mode dashboards are never searched on either path — the component walk skips them in-process and the component-less legacy walk skips any row tagged mode="yaml" — because HA resolves !secret when loading a YAML Lovelace config, so searching one could surface resolved secrets. On installs without the ha_mcp_tools component, the default (unnamed) dashboard is also not searched — only dashboards with a url_path are.

Return a stable config_hash (Get and Search modes only; not present in list_only mode) across consecutive reads of an unchanged config — compute_config_hash documents the underlying contract.

EXAMPLES:

• List all dashboards: ha_config_get_dashboard(list_only=True)

• Get default dashboard: ha_config_get_dashboard(url_path="default")

• Get custom dashboard: ha_config_get_dashboard(url_path="lovelace-mobile")

• Get one view only: ha_config_get_dashboard(url_path="lovelace-mobile", view_path="office")

• Force reload: ha_config_get_dashboard(url_path="lovelace-home", force_reload=True)

• Find cards by entity: ha_config_get_dashboard(url_path="my-dash", entity_id="light.living_room")

• Find by wildcard: ha_config_get_dashboard(url_path="my-dash", entity_id="sensor.temperature_*")

• Find by type: ha_config_get_dashboard(url_path="my-dash", card_type="tile")

• Find heading: ha_config_get_dashboard(url_path="my-dash", heading="Climate", card_type="heading")

SEARCH WORKFLOW EXAMPLE:

1. find = ha_config_get_dashboard(url_path="my-dash", entity_id="light.bedroom")

2. ha_config_set_dashboard( url_path="my-dash", config_hash=find["config_hash"], python_transform=f'config{find["matches"][0]["python_path"]}["icon"] = "mdi:lamp"' )

Note: YAML-mode dashboards (defined in configuration.yaml) are not included in list.