happ_test_case_create

SERVERPlatform SOURCE@happ-ai/platform-mcp

Low RISK CLASS

Category Read

Parameters 123 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/happ-ai-platform-mcp/happ-test-case-create.md

WHAT IT DOES

What happ_test_case_create does on Platform

AI agents call happ_test_case_create to retrieve information from Platform without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Parameter	Type	Required	Description
`mode`	string	Yes	Режим кейса
`name`	string	Yes	Короткое название кейса
`enabled`	boolean	—	Участвует ли в «прогнать все» (по умолчанию true)
`scenario`	string	—	Сценарий клиента с целью (только для scenario)
`toolMocks`	array	—	Моки инструментов ЭТОГО кейса: инструмент не вызывает реальную систему, а возвращает мок. Побеждают над общими моками ассистента по имени инструмента
`maxCostUsd`	object	—	Лимит в долларах: оборвать прогон при превышении оценочной стоимости кейса (null — снять лимит)
`assistantId`	string	Yes	ID ассистента
`attachments`	array	—	Фото, которые клиент отправит в диалоге (mediaId из happ_test_media_upload)
`maxMessages`	object	—	Лимит: оборвать прогон, когда общее число сообщений в диалоге превысит это значение (null — снять лимит)
`seedMessages`	array	—	Переписка, которая БЫЛА до теста: она пишется в чат перед диалогом, и ассистент читает её как настоящую историю. Так проверяется постоянный клиент, который пише
`userMessages`	array	—	Реплики клиента (только для script)
`dynamicVariables`	object	—	Значения {{плейсхолдеров}} промпта на время прогона (имя -> значение)

Parameters from the server's own tool schema.

RISK

Why happ_test_case_create is rated Low

Even though happ_test_case_create only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.

Risk signalsHigh parameter count (25 properties)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs happ_test_case_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_test_case_create, this is the rule to start with:

happ_test_case_create Allowed

happ_test_case_create is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "happ_test_case_create": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Platform, apply this rule, and every happ_test_case_create call is checked against it from then on.

FAQ

Questions about happ_test_case_create

What does the happ_test_case_create tool do? +

Создаёт тест-кейс. mode=script — фиксированные реплики клиента (1-3, для точечных проверок формулировок); mode=scenario — описание клиента для AI-симулятора (для многоходовых флоу). Сценарий ОБЯЗАН заканчиваться строками «Мета досягнута, коли …» и «Не погоджуйся на додаткові пропозиції…» — иначе диалог тянется до капа 12 ходов и жжёт токены. Фото клиента: сначала happ_test_media_upload, затем передай attachments с mediaId. seedMessages — переписка, которая была ДО теста (постоянный клиент, чей адрес и товар уже известны из прошлых заказов). (POST /assistants/:assistantId/test-cases). It is categorised as a Read tool in the Platform MCP Server, which means it retrieves data without modifying state.

What parameters does happ_test_case_create accept? +

happ_test_case_create accepts 12 parameters: mode, name, enabled, scenario, toolMocks, maxCostUsd, assistantId, attachments, maxMessages, seedMessages, userMessages, dynamicVariables. Required: mode, name, assistantId. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on happ_test_case_create? +

Register the Platform MCP server in PolicyLayer and add a rule for happ_test_case_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.

What risk level is happ_test_case_create? +

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

Can I rate-limit happ_test_case_create? +

Yes. Add a rate_limit block to the happ_test_case_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.

How do I block happ_test_case_create completely? +

Set action: deny in the PolicyLayer policy for happ_test_case_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.

What MCP server provides happ_test_case_create? +

happ_test_case_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.

KEEP EXPLORING

More on Platform, and thousands of servers like it.

This server

All 275 Platform tools →

Across the catalogue

The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →