Skip to main content
Glama
Sign In
Home Assistant MCP Server

Home Assistant MCP Server

by rilhia
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Get dashboard config

get_dashboard
Read-onlyIdempotent

Reads a Home Assistant dashboard's stored configuration, returning a view summary by default or a specific view or full config when requested.

Instructions

Read a dashboard's stored configuration. By default returns a summary of its views. Set view to a view path, title or index to read one view in full, or full true for the whole config. Auto generated dashboards have no stored config.

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": "get_dashboard"
  }
}

Input Schema

NameRequiredDescriptionDefault
fullNoReturn the entire config. Can be large.
viewNoA view's path, title or index. Returns just that view's full config.
url_pathNoDashboard url_path, for example 'dashboard-house'. Omit for the default Overview dashboard.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.1

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavioral context: the default is a summary rather than the full config, the alternate modes, and that auto-generated dashboards have no stored config to return.

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?

Four short sentences, front-loaded with the verb+resource and then the default behavior before the options. Only the phrasing 'or full true for the whole config' is slightly compressed, but nothing is wasted and the caveat earns its place.

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?

With no output schema, the description carries the burden of describing returns and does so at the right granularity: summary of views by default, one view in full, or the whole config. Combined with the edge-case note about auto-generated dashboards, an agent has enough to call this correctly.

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

Parameters3/5

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

Schema coverage is 100% and each parameter already documents itself, including 'Can be large' on full and the url_path example. The description restates the view/full semantics but adds little the schema does not, and never clarifies how view and full interact if both are set.

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

Purpose4/5

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

States a specific verb and resource: 'Read a dashboard's stored configuration.' An agent can immediately tell this retrieves config rather than listing dashboards, though it never names the sibling list_dashboards that would be the natural discovery step.

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?

Gives clear mode selection: default summary, 'view' for one view in full, 'full true' for everything, plus an exclusion edge case ('Auto generated dashboards have no stored config'). It stops short of saying when to prefer this over list_dashboards or when full=true is inappropriate beyond size.

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