Skip to main content
Glama
homeassistant-ai

Home Assistant MCP Server

Official

Manage Assist Pipeline

ha_manage_pipeline
Destructive

List, inspect, create, update, and set preferred Assist pipelines, or process natural-language commands through Home Assistant Assist to execute intents.

Instructions

Manage Home Assistant Assist pipelines.

Use action='list' to discover pipeline IDs, action='get' to inspect one pipeline, action='create' or action='update' to write pipeline settings, action='set_preferred' to choose the preferred pipeline, and action='process' to run a sentence through Assist.

action='process' sends the sentence straight to Assist's conversation agent, so a matched intent executes: it turns on the light rather than reporting that it would. Its result carries response_type ('action_done', 'query_answer' or 'error') and, on an error, error_code such as 'no_intent_match' — Assist declining a sentence is an answer, not a tool failure, so inspect those fields rather than expecting a raised error. Use ha_call_service to act on an entity directly; use this to test what Assist itself understands. When the built-in agent answers, a matching conversation trigger runs its automation: that agent checks its sentence triggers before it matches intents, so this is not limited to intents. pipeline_id borrows a pipeline's conversation agent and language, but the sentence still goes to the agent directly. So with an agent other than the built-in one, neither sentence triggers nor prefer_local_intents apply — a full pipeline run is what adds those for other agents.

EXAMPLES:

  • List pipelines: ha_manage_pipeline(action="list")

  • Get one pipeline: ha_manage_pipeline(action="get", pipeline_id="preferred")

  • Create by cloning preferred: ha_manage_pipeline( action="create", name="Local Assist", conversation_engine="conversation.local_llm", )

  • Create by cloning a specific pipeline: ha_manage_pipeline( action="create", base_pipeline_id="preferred", name="Local Assist", conversation_engine="conversation.local_llm", )

  • Update conversation agent and clear TTS voice: ha_manage_pipeline( action="update", pipeline_id="preferred", conversation_engine="conversation.local_llm", tts_voice="", )

  • Set preferred: ha_manage_pipeline( action="set_preferred", pipeline_id="preferred", )

  • Run a sentence: ha_manage_pipeline( action="process", sentence="turn on the kitchen light", )

  • Run it through one pipeline's agent: ha_manage_pipeline( action="process", sentence="turn on the kitchen light", pipeline_id="preferred", )

  • Continue a conversation: ha_manage_pipeline( action="process", sentence="and the hallway?", conversation_id="", )

Empty string clears nullable STT/TTS/wake-word fields. Non-nullable fields such as name, language, conversation_language, and conversation_engine must be omitted or non-empty.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNoPipeline display name. Required when action='create'.
actionYesPipeline operation: list, get, create, update, set_preferred, or process.
agent_idNoFor process only, the conversation agent entity ID to answer, e.g. 'conversation.home_assistant'. Overrides the agent taken from pipeline_id; omit both for the default agent.
languageNoPipeline language, e.g. 'en'. For process, the language to recognise the sentence in.
sentenceNoNatural-language command to run through Assist. Required when action='process'. A matched intent executes, and with the built-in agent a sentence matching a conversation trigger runs that automation.
tts_voiceNoText-to-speech voice. Pass empty string to clear.
stt_engineNoSpeech-to-text engine. Pass empty string to clear.
tts_engineNoText-to-speech engine. Pass empty string to clear.
pipeline_idNoAssist pipeline ID. Required for get, update, and set_preferred. Optional for process, where it selects the conversation agent and language that pipeline is configured with.
stt_languageNoSpeech-to-text language. Pass empty string to clear.
tts_languageNoText-to-speech language. Pass empty string to clear.
wake_word_idNoWake-word ID. Pass empty string to clear.
make_preferredNoFor create/update only, also set the resulting pipeline as preferred with an extra websocket call. Ignored for other actions.
conversation_idNoFor process only, the conversation to continue. Returned in the response so follow-up sentences keep their context.
base_pipeline_idNoPipeline ID to clone when creating. Omit to clone the preferred pipeline. Ignored for non-create actions.
wake_word_entityNoWake-word entity ID. Pass empty string to clear.
conversation_engineNoConversation agent entity ID or engine ID. Required when action='create'.
prefer_local_intentsNoWhether Home Assistant local intents should be preferred before the conversation engine.
conversation_languageNoConversation language, usually '*'.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed7 schema fields changedv8.3.0
    • changedInput schema / properties / action / description
      Previous value: -"Pipeline operation: list, get, create, update, or set_preferred."New value: +"Pipeline operation: list, get, create, update, set_preferred, or process."
    • changedInput schema / properties / action / enum
      Previous value: -[
      -  "list",
      -  "get",
      -  "create",
      -  "update",
      -  "set_preferred"
      -]New value: +[
      +  "list",
      +  "get",
      +  "create",
      +  "update",
      +  "set_preferred",
      +  "process"
      +]
    • addedInput schema / properties / agent_id
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "For process only, the conversation agent entity ID to answer, e.g. 'conversation.home_assistant'. Overrides the agent taken from pipeline_id; omit both for the default agent."
      +}
    • addedInput schema / properties / conversation_id
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "For process only, the conversation to continue. Returned in the response so follow-up sentences keep their context."
      +}
    • changedInput schema / properties / language / description
      Previous value: -"Pipeline language, e.g. 'en'."New value: +"Pipeline language, e.g. 'en'. For process, the language to recognise the sentence in."
    • changedInput schema / properties / pipeline_id / description
      Previous value: -"Assist pipeline ID. Required for get, update, and set_preferred."New value: +"Assist pipeline ID. Required for get, update, and set_preferred. Optional for process, where it selects the conversation agent and language that pipeline is configured with."
    • addedInput schema / properties / sentence
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Natural-language command to run through Assist. Required when action='process'. A matched intent executes, and with the built-in agent a sentence matching a conversation trigger runs that automation."
      +}
  2. First observedv7.14.2

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=true), the description adds rich behavioral context: it explains that action='process' executes intents ('it turns on the light rather than reporting that it would'), that errors are returned as fields ('does not raise an error'), and that conversation triggers only apply to the built-in agent. It also discloses the empty-string-clearing convention and the extra websocket call for make_preferred. This is far beyond annotation expectations.

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 with the action list, then dives into important behavioral nuances and examples. While long, it earns its place by covering six distinct actions and complex edge cases (e.g., agent-specific behavior). The examples are well-organized and labeled. It loses a point for density—the process paragraph is a wall of text that could be broken up for easier scanning—but overall remains efficient for a complex tool.

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 tool with 19 parameters and six actions, the description is remarkably complete. It covers error handling ('Assist declining a sentence is an answer, not a tool failure'), agent behavior ('conversation triggers... are not limited to intents'), multiple examples, and the empty-string-clearing convention. The output schema is also present, and the description complements it without redundancy. No gaps identified.

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?

The schema already has 100% coverage, so baseline is 3. The description adds value beyond the schema by explaining interaction semantics, e.g., that conversation_id is used for follow-ups, base_pipeline_id cloning behavior, and that pipeline_id is required for certain actions. The extensive examples further clarify parameter usage. It doesn't repeat schema descriptions verbatim but adds contextual meaning (e.g., the process action's side effects), so a 4 is warranted.

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 clearly states the tool's purpose: 'Manage Home Assistant Assist pipelines' and then enumerates the six actions (list, get, create, update, set_preferred, process). It distinguishes this tool from its sibling by specifying 'Use ha_call_service to act on an entity directly; use this to test what Assist itself understands.' This is a specific verb+resource with clear scope and sibling differentiation.

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?

The description explicitly provides usage guidelines with a direct alternative: 'Use ha_call_service to act on an entity directly; use this to test what Assist itself understands.' It also differentiates when to use each action (e.g., 'action="list" to discover pipeline IDs', 'action="process" to run a sentence through Assist'). It further clarifies behavior with the built-in agent versus other agents, giving concrete when-to-use and when-not-to-use guidance.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/homeassistant-ai/ha-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server