# OpenUI Cloud — how to use (mcp.ai)

Connect your OpenUI Cloud account and use 8 tools for AI content generation straight from your AI agent. Connect with your own API key. OpenUI Cloud by Thesys generates interactive user interfaces and manages conversations and artifacts through OpenAI-compatible APIs.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_openui?ms=1787293740000`
Add it as a custom/remote MCP connector in your client (Claude, Cursor, VS Code…), then authenticate when prompted. Once connected, ask the agent to use the server's tools (e.g. `openui_create_conversation`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/openui`
Auth: `Authorization: Bearer sk_live_…` — create a workspace API key at https://mcp.ai/settings/api-keys
Discover endpoints: `GET https://api.mcp.ai/api/openui/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/openui/create/conversation` — Create a managed OpenUI conversation that can receive persisted turns from Generate UI.
  - body: { title?: string }
- `POST https://api.mcp.ai/api/openui/delete/conversation` — Permanently delete one managed OpenUI conversation by ID.
  - body: { conversation_id: string }
- `POST https://api.mcp.ai/api/openui/generate/ui` — Generate an OpenUI response from text or structured Responses API input. Supports standalone generation, stored-response chaining, managed conversations, Cloud-native tools, and caller-owned function 
  - body: { input: string|object[], model: string, store?: boolean, tools?: object[], temperature?: number, tool_choice?: string|object, instructions?: string, conversation_id?: string, reasoning_effort?: string, max_output_tokens?: integer, parallel_tool_calls?: boolean, previous_response_id?: string }
- `POST https://api.mcp.ai/api/openui/get/artifact` — Retrieve one persisted OpenUI artifact, including its complete renderable content.
  - body: { artifact_id: string }
- `POST https://api.mcp.ai/api/openui/list/artifacts` — List persisted OpenUI artifacts, optionally filtering by name or artifact kinds, one cursor-controlled page at a time.
  - body: { name?: string, kinds?: string[], limit?: integer, next_cursor?: string }
- `POST https://api.mcp.ai/api/openui/list/conversation/items` — Read one cursor-controlled page of persisted messages and function-call items from a managed OpenUI conversation.
  - body: { limit?: integer, order?: string, next_cursor?: string, conversation_id: string }
- `POST https://api.mcp.ai/api/openui/list/conversations` — List managed OpenUI conversations visible to the connected organization, one cursor-controlled page at a time.
  - body: { limit?: integer, next_cursor?: string }
- `POST https://api.mcp.ai/api/openui/rename/conversation` — Change the title of an existing managed OpenUI conversation.
  - body: { title: string, conversation_id: string }

## Example prompts
- "What can I do in OpenUI Cloud?"
- "Show me a summary of my OpenUI Cloud account"

## More
- Page: https://mcp.ai/openui
- Agent spec (llms.txt): https://mcp.ai/openui/llms.txt
- Postman collection: https://mcp.ai/openui/postman.json