Skip to main content
Glama

Manage Updates

ha_manage_updates
Destructive

List, inspect, install, or skip Home Assistant updates across Core, OS, apps, firmware, and HACS, and dismiss or restore Repairs issues with read-only safeguards.

Instructions

Manage Home Assistant updates (list, details, install, skip) and Repairs issues (ignore).

Covers Core, OS, supervisor, apps (add-ons), device firmware, and HACS update entities, plus the Repairs issues in Settings > System > Repairs. Repairs are listed by ha_get_overview (not here); pass their domain and issue_id to 'ignore_repair' / 'unignore_repair'. In Read Only Mode the read actions ('list', 'get') stay available; write actions are blocked.

'install' blocks until each update finishes (minutes). One that outlasts the request timeout ends the call with a connection timeout while it keeps running, and a Core update restarts Home Assistant; neither means failure, but later batch targets were not started. Confirm per entity with action='get'; finished updates drop out of 'list', which also returns ha_mcp_update — this MCP server's own update status {current, latest, update_available}, so a newer ha-mcp release can be flagged.

EXAMPLES:

  • Pre-update analysis: ha_manage_updates(action="get", entity_ids=["update.home_assistant_core_update"], include_release_notes=True)

  • Update everything pending in a category: ha_manage_updates(action="install", categories=["addons", "hacs"])

  • Dismiss a repair: ha_manage_updates(action="ignore_repair", repairs=[{"domain": "sun", "issue_id": "abc"}])

If a Claude Desktop user gets a 4-minute timeout with no result on this call, read the target back before repeating it, and tell them to wait a few seconds before clicking the manual-approve button, as clicking it too quickly is known to cause hangs in Claude Desktop. This workaround is specific to Claude Desktop.

update updates install skip firmware core os repair repairs issue ignore dismiss unignore

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_manage_updates"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionNo'list' (all pending updates, default), 'get' (details/release notes for one update), 'install' (apply pending updates), 'skip' (hide the offered version), 'clear_skipped' (re-offer a skipped version), 'ignore_repair' (dismiss Repairs issues, as the Repairs UI's Ignore does), or 'unignore_repair' (show them again).list
backupNoFor install: create a backup before installing where the update entity supports it (apps (add-ons)).
repairsNoFor ignore_repair / unignore_repair: the Repairs issues to act on, as [{'domain': ..., 'issue_id': ...}] taken from ha_get_overview's repairs.
categoriesNoFor install: apply every pending update in these categories ('addons', 'hacs', 'devices', 'other'). As with the HA 'Update all' button, core/os/supervisor are excluded (target those individually via entity_ids) and skipped updates are never included.
entity_idsNoUpdate entity_id(s) to act on. 'get' takes exactly one; skip/clear_skipped require at least one; for install, mutually exclusive with categories.
include_skippedNoFor list: include updates that have been skipped.
include_release_notesNoFor get on a Core update entity: fetch multi-version release notes and breaking changes for all versions between installed and latest. Adds breaking_changes, multi_version_release_notes, and installed_integrations to the response.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv9.2.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already flag destructive and non-read-only behavior, but the description adds substantial beyond-schema context: install blocks for minutes, timeout can occur while the update continues, Core updates restart Home Assistant, batch targets after a timeout may not have started, and finished updates disappear from list. It also notes the Claude Desktop timeout workaround and the ha_mcp_update status returned by list.

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 description is front-loaded and well organized for a complex multi-action tool, moving from purpose to scope to special cases and examples. It is on the long side and includes a keyword tail plus a very specific Claude Desktop workaround, but the length is largely justified by the tool's complexity and destructive operations.

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?

Given the rich input schema, output schema, annotations, and the tool's complexity, the description covers the key operational caveats an agent needs: read-only mode behavior, repair listing source, install blocking/timeout semantics, post-install verification, and the extra ha_mcp_update status. No critical call-selection context appears missing.

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 description coverage is 100%, so the schema already documents the parameters in detail. The description reinforces some semantics—repairs come from ha_get_overview, categories exclude core/os/supervisor, entity_ids constraints for get/skip/install—but much of this repeats the schema rather than adding format or behavior the schema lacks.

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 description opens with a specific verb+resource and enumerates the actions: list/get/install/skip for updates and ignore/unignore for Repairs. It also distinguishes the scope from siblings by explicitly saying Repairs are listed by ha_get_overview, not here, and mentions ha_mcp_update returned by list.

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

Usage Guidelines5/5

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

It gives clear routing guidance: Repairs are listed by ha_get_overview and passed here as domain/issue_id, read actions remain available in Read Only Mode while writes are blocked, and install categories exclude core/os/supervisor so those must be targeted individually. The examples reinforce the main usage patterns without leaving alternatives implicit.

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