Skip to main content
Glama

integrations_update_integration_entry

Update an existing integration entry's title, disable new entities, or disable polling to customize Home Assistant integration behavior.

Instructions

Update properties of an existing config entry (title, polling preferences).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
entry_idYes
titleNo
pref_disable_new_entitiesNo
pref_disable_pollingNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • The `update_integration_entry` function is the handler for the 'integrations_update_integration_entry' tool. It updates an existing Home Assistant config entry by calling the WebSocket API method 'config_entries/update' with optional title, pref_disable_new_entities, and pref_disable_polling parameters. It is decorated with @mcp.tool() so it auto-registers as an MCP tool.
    @mcp.tool()
    def update_integration_entry(
        entry_id: str,
        title: str | None = None,
        pref_disable_new_entities: bool | None = None,
        pref_disable_polling: bool | None = None,
    ) -> dict:
        """Update properties of an existing config entry (title, polling preferences)."""
        payload: dict = {"entry_id": entry_id}
        if title is not None:
            payload["title"] = title
        if pref_disable_new_entities is not None:
            payload["pref_disable_new_entities"] = pref_disable_new_entities
        if pref_disable_polling is not None:
            payload["pref_disable_polling"] = pref_disable_polling
        return ha._ws_call("config_entries/update", **payload)
  • server.py:55-55 (registration)
    The 'integrations' namespace is mounted on the main MCP server at line 55, meaning this tool becomes accessible as 'integrations_update_integration_entry' (namespace + tool name).
    mcp.mount(integrations_mcp, namespace="integrations")
  • The integrations MCP server is created with the name 'integrations'. The @mcp.tool() decorator on update_integration_entry registers it as a tool within this server.
    mcp = FastMCP("integrations")
  • The `_ws_call` helper function sends a WebSocket call to Home Assistant with the specified message type and keyword arguments. The 'update_integration_entry' handler calls this with msg_type='config_entries/update'.
    def _ws_call(msg_type: str, **kwargs) -> Any:
        try:
            asyncio.get_running_loop()
        except RuntimeError:
            return asyncio.run(_ws_call_async(msg_type, **kwargs))
        import concurrent.futures
        with concurrent.futures.ThreadPoolExecutor() as pool:
            return pool.submit(asyncio.run, _ws_call_async(msg_type, **kwargs)).result()
  • The `_ws_call_async` helper function that actually opens a WebSocket connection to Home Assistant, authenticates, sends the message (e.g., 'config_entries/update'), and returns the result.
    async def _ws_call_async(msg_type: str, **kwargs) -> Any:
        import websockets
        token = _HA_TOKEN
        # max_size=None disables the 1 MB frame cap — HACS repository lists,
        # large registries and full traces routinely exceed that.
        async with websockets.connect(_ws_url(), max_size=None) as ws:
            greeting = json.loads(await ws.recv())
            assert greeting["type"] == "auth_required"
            await ws.send(json.dumps({"type": "auth", "access_token": token}))
            auth_ok = json.loads(await ws.recv())
            if auth_ok["type"] != "auth_ok":
                raise RuntimeError(f"WS auth failed: {auth_ok}")
            payload = {"id": 1, "type": msg_type, **kwargs}
            await ws.send(json.dumps(payload))
            while True:
                data = json.loads(await asyncio.wait_for(ws.recv(), timeout=10))
                if data.get("id") == 1 and data.get("type") == "result":
                    if not data.get("success"):
                        raise RuntimeError(f"WS error: {data.get('error')}")
                    return data["result"]
Behavior2/5

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

With no annotations, the description must disclose behavioral traits. It only states it updates properties, but fails to mention idempotency, side effects, required states, or response behavior. Output schema exists but is not referenced.

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 a single sentence with no redundant words, achieving high conciseness. However, it sacrifices informativeness, so while structurally efficient, it is under-specified.

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

Completeness2/5

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

Given 4 parameters, no annotations, and an output schema, the description is too brief. It does not explain what a config entry is, when updates take effect, or error cases, leaving significant gaps for safe usage.

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

Parameters2/5

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

Schema coverage is 0%, and the description adds minimal meaning: it groups 'polling preferences' but does not explain individual parameters like 'pref_disable_new_entities'. The mapping is incomplete and lacks detail.

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 verb 'Update' and the resource 'config entry', and specifies the properties 'title' and 'polling preferences'. This differentiates it from sibling tools like disable, enable, or remove integration.

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

Usage Guidelines2/5

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

No guidance is provided on when to use this tool versus alternatives, nor any prerequisites or exclusions. The description is minimal and does not help the agent decide context.

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/Fistacho/ha-nexus-agent'

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