happ_knowledge_create
Добавляет запись в базу знаний ассистента: текст (type=text + resourceContent), ссылку (type=url + resourceUrl) или загруженный файл (type=file + fileId — текст извлекается платформой, перепечатывать содержимое не нужно). (POST /assistant-knowledge-new)
This record as markdown: /tools/happ-ai-platform-mcp/happ-knowledge-create.md
What happ_knowledge_create does on Platform
AI agents use happ_knowledge_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 | Название записи |
type | string | — | Тип знания: url (ссылка), text (текст), file (файл из /files — передай fileId) |
fileId | string | — | ID загруженного файла (pdf/docx/txt/md/csv), например вложение из чата копилота; платформа сама извлечёт текст. Требует type=file |
isVector | boolean | — | Storage type: true = Vector DB (содержимое чанкуется и индексируется в векторную базу — ПЛАТНАЯ индексация, списывает LLM-кредиты компании; включай только когда |
assistantId | string | Yes | ID ассистента |
resourceUrl | string | — | URL источника (обязателен при type=url) |
itemDelimiter | string | — | Разделитель записей при chunkingStrategy=items (например "\n\n---\n\n") |
resourceContent | string | — | Текстовое содержимое знания (для type=text) |
chunkingStrategy | string | — | Стратегия чанкинга для Vector DB: tokens (по умолчанию, для сплошного текста) или items (для списков однотипных карточек — товары, FAQ; записи разделяются itemD |
resourceDescription | string | — | Описание источника |
Parameters from the server's own tool schema.
Why happ_knowledge_create is rated Medium
An AI agent can call happ_knowledge_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 (10 properties)
Attacks that exploit this kind of access
The rule that runs happ_knowledge_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_knowledge_create, this is the rule to start with:
happ_knowledge_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_knowledge_create call is checked against it from then on.
Questions about happ_knowledge_create
Добавляет запись в базу знаний ассистента: текст (type=text + resourceContent), ссылку (type=url + resourceUrl) или загруженный файл (type=file + fileId — текст извлекается платформой, перепечатывать содержимое не нужно). (POST /assistant-knowledge-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_knowledge_create accepts 10 parameters: name, type, fileId, isVector, assistantId, resourceUrl, itemDelimiter, resourceContent, chunkingStrategy, resourceDescription. Required: name, 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_knowledge_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_knowledge_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_knowledge_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_knowledge_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_knowledge_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