happ_assistant_create
Создаёт AI-ассистента в компании. Обязательны companyId и name. Провайдера, голос и модели НЕ передавай, если пользователь их не назвал: платформа ставит стандарт нового агента (голос Gemini 3.8 Live, Erinome; текст gpt-5.4). Провижининг в VA идёт асинхронно — статус смотри в registration.syncSta...
This record as markdown: /tools/happ-ai-platform-mcp/happ-assistant-create.md
What happ_assistant_create does on Platform
AI agents use happ_assistant_create to create or update resources in Platform, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Platform environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
name | string | Yes | Имя ассистента |
voiceId | string | — | ID голоса из VA-каталога (happ_voices_list) |
folderId | object | — | Папка ассистента (общее) |
language | string | — | Язык ассистента, например 'ru' или 'uk' |
timezone | string | — | Таймзона ассистента, например Europe/Kyiv (общее) |
companyId | string | Yes | ID компании |
eagerness | string | — | ГОЛОС · «Активность»: как быстро ассистент начинает отвечать — eager (Активный, отвечает быстро), normal (Обычный), patient (Терпеливый, ждёт, пока клиент точно |
isDefault | boolean | — | Ассистент по умолчанию для компании (общее) |
promptText | string | — | Системный промпт (инструкции) ассистента |
providerId | string | — | Конкретный голосовой провайдер из happ_voice_providers_list (id строки), в т.ч. приватный провайдер из своего ключа (isPrivate=true). Задаёт провайдера точнее, |
softTimeout | number | — | ГОЛОС · «Мягкий таймаут»: сколько секунд ждать ответ LLM, прежде чем сказать промежуточную фразу softTimeoutMessage (0.5–8); -1 = выключено |
firstMessage | string | — | Первое сообщение ассистента |
Parameters from the server's own tool schema.
Why happ_assistant_create is rated Medium
An AI agent can call happ_assistant_create faster than any human can review: one bad instruction and it creates or modifies resources in Platform by the hundred, each call as confident as the last.
Risk signalsHigh parameter count (25 properties)
Attacks that exploit this kind of access
The rule that runs happ_assistant_create safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Platform, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For happ_assistant_create, this is the rule to start with:
happ_assistant_create stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Platform, apply this rule, and every happ_assistant_create call is checked against it from then on.
Questions about happ_assistant_create
Создаёт AI-ассистента в компании. Обязательны companyId и name. Провайдера, голос и модели НЕ передавай, если пользователь их не назвал: платформа ставит стандарт нового агента (голос Gemini 3.8 Live, Erinome; текст gpt-5.4). Провижининг в VA идёт асинхронно — статус смотри в registration.syncStatus через happ_assistant_get. (POST /assistants-new). It is categorised as a Write tool in the Platform MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
happ_assistant_create accepts 12 parameters: name, voiceId, folderId, language, timezone, companyId, eagerness, isDefault, promptText, providerId, softTimeout, firstMessage. Required: name, companyId. The full parameter table on this page comes from the server's own tool schema.
Register the Platform MCP server in PolicyLayer and add a rule for happ_assistant_create: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Platform. Nothing to install.
happ_assistant_create is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the happ_assistant_create rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for happ_assistant_create. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
happ_assistant_create is provided by the Platform MCP server (@happ-ai/platform-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Platform, and thousands of servers like it.
This server
Across the catalogue