happ_test_media_upload
Загружает фото, которое «клиент отправит» в тестовом диалоге. Источник — ровно один из: fileId (файл уже загружен в платформу, например вложение из чата копилота — единственный вариант в копилоте), filePath (путь к файлу, ~ поддерживается), clipboard=true (картинка из буфера обмена macOS — попрос...
This record as markdown: /tools/happ-ai-platform-mcp/happ-test-media-upload.md
What happ_test_media_upload does on Platform
AI agents call happ_test_media_upload 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 |
|---|---|---|---|
url | string | — | Прямая ссылка на изображение |
fileId | string | — | ID файла из /files (вложение чата копилота) |
filePath | string | — | Путь к файлу изображения на компьютере пользователя |
clipboard | boolean | — | Взять картинку из буфера обмена macOS |
assistantId | string | Yes | ID ассистента (определяет компанию для загрузки) |
Parameters from the server's own tool schema.
Why happ_test_media_upload is rated Low
Even though happ_test_media_upload 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 signalsAccepts file system path (filePath) · Accepts URL/endpoint input (url)
Attacks that exploit this kind of access
The rule that runs happ_test_media_upload 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_media_upload, this is the rule to start with:
happ_test_media_upload is read-only, so it stays allowed. 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_test_media_upload call is checked against it from then on.
Questions about happ_test_media_upload
Загружает фото, которое «клиент отправит» в тестовом диалоге. Источник — ровно один из: fileId (файл уже загружен в платформу, например вложение из чата копилота — единственный вариант в копилоте), filePath (путь к файлу, ~ поддерживается), clipboard=true (картинка из буфера обмена macOS — попроси пользователя скопировать фото через ⌘C), url (прямая ссылка). Платформа сразу отправляет фото на VLM-распознавание; в ответе mediaId — передай его в attachments при создании кейса. Описание генерится асинхронно (~5-30с): прогон теста сам дождётся готовности. (POST /assistants/:assistantId/test-cases/media). It is categorised as a Read tool in the Platform MCP Server, which means it retrieves data without modifying state.
happ_test_media_upload accepts 5 parameters: url, fileId, filePath, clipboard, assistantId. Required: assistantId. 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_test_media_upload: 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_test_media_upload is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the happ_test_media_upload 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_test_media_upload. 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_test_media_upload 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