consult_service

Сервисная консультация по обслуживанию бассейна (все типы: композитный, бетонный, полипропиленовый, каркасный). Поток: готовый ответ из базы знаний → промах → заявка с номером (буква+2 цифры, напр. А05), AI готовит черновик async, специалист получает заявку на почту. Темы: запуск/залив, слив, ухо...

Server Laguna Pools https://mcp.laguna-pools.ru/api/mcp/
Category Read
Risk class Low
Parameters 80 required

What consult_service does on Laguna Pools

AI agents call consult_service to retrieve information from Laguna Pools without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

ParameterTypeRequiredDescription
mode string ask — задать вопрос; status — проверить ответ по номеру заявки; contact — сохранить контакт по заявке; escalate — передать заявку живому специалисту
channel string Канал связи: whatsapp|telegram|viber|email (опционально)
contact string Контакт клиента (телефон/email, для mode=contact)
user_id string ID аккаунта Алисы (для памяти заявок)
question string Вопрос по обслуживанию бассейна (для mode=ask, до 500 символов)
pool_type string Тип бассейна (опционально): composite, concrete, polypropylene, frame, all
ticket_no string Номер заявки (для mode=status/contact/escalate)
session_id string ID сессии (для журнала)

Parameters from the server's own tool schema.

Why consult_service needs a policy

The tool's primary function is to query and retrieve maintenance advice from a knowledge base for swimming pools. While it can create support tickets as a secondary action, ticket creation is a simple administrative record (similar to logging an inquiry) rather than a modification of customer data or system state. No code execution, data deletion, financial transactions, or irreversible changes occur.

From the tool's definition Tool provides 'Сервисная консультация' (service consultation) with answers from a knowledge base ('готовый ответ из базы знаний'), optionally creating support tickets ('заявка').

Questions about consult_service

What does the consult_service tool do? +

Сервисная консультация по обслуживанию бассейна (все типы: композитный, бетонный, полипропиленовый, каркасный). Поток: готовый ответ из базы знаний → промах → заявка с номером (буква+2 цифры, напр. А05), AI готовит черновик async, специалист получает заявку на почту. Темы: запуск/залив, слив, уход, химия воды, оборудование, тепло, консервация, проблемы, безопасность. Защита от нецелевых запросов, инъекций и мата. It is categorised as a Read tool in the Laguna Pools MCP Server, which means it retrieves data without modifying state.

What parameters does consult_service accept? +

consult_service accepts 8 parameters: mode, channel, contact, user_id, question, pool_type, ticket_no, session_id. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on consult_service? +

Register the Laguna Pools MCP server in PolicyLayer and add a rule for consult_service: 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 Laguna Pools. Nothing to install.

What risk level is consult_service? +

consult_service is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit consult_service? +

Yes. Add a rate_limit block to the consult_service 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.

How do I block consult_service completely? +

Set action: deny in the PolicyLayer policy for consult_service. 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.

What MCP server provides consult_service? +

consult_service is provided by the Laguna Pools MCP server (https://mcp.laguna-pools.ru/api/mcp/). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER SERVER

Every MCP server has a record like this.

Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.