OpenUI Cloud for AI agents

OpenUI Cloud by Thesys generates interactive user interfaces from prompts and manages the conversations and artifacts behind them. Product teams use it to prototype UI screens quickly. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Connect OpenUI Cloud See the 8 actions ↓

AI and modelsAPI keyMCP + RESTthesys.dev

AUDIT LOG · OPENUI CLOUDPOLICY: acme-support

09:41:07 · claude · u_8f2read

openui_cloud.list_artifacts

List Artifacts✓ allowed · 212ms

09:41:08 · claude · u_8f2read

openui_cloud.get_artifact

Get Artifact✓ allowed · 164ms

09:41:09 · claude · u_8f2write

openui_cloud.create_conversation

Create Conversation✓ approved · approved by user

09:41:12 · claude · u_8f2destructive

openui_cloud.delete_conversation

Delete Conversation✕ blocked · policy: deny

EVERY OPENUI CLOUD CALL, ON THE RECORD

01 · USE CASES

What agents do in OpenUI Cloud.

Generate a UI from a prompt

Create an interactive interface mockup from a description of the screen needed.

List saved artifacts read-only

Check previously generated UI artifacts before creating a new variation.

Delete a conversation with approval

Remove an old conversation thread only after confirming its artifacts are no longer needed.

02 · ACTIONS

8 OpenUI Cloud actions, graded by risk.

Every OpenUI Cloud action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

Look things up. Allowed by default.

openui_cloud.get_artifact
Get Artifact
openui_cloud.list_artifacts
List Artifacts
openui_cloud.list_conversations
List Conversations
openui_cloud.list_conversation_items
List Conversation Items

write

Create and change things. Allow, or ask the user first.

openui_cloud.create_conversation
Create Conversation
openui_cloud.generate_ui
Generate UI
openui_cloud.rename_conversation
Rename Conversation

destructive

Delete, cancel or archive. Ask first, or deny outright.

openui_cloud.delete_conversation
Delete Conversation

03 · HOW IT WORKS

OpenUI Cloud in three steps.

01Your users connect OpenUI CloudThey add their OpenUI Cloud api key on Arc0 Connect, under your brand. It goes straight into the vault.
02You set the rulesReads run, writes like “create Conversation” can wait for the user, and “delete Conversation” can be denied outright.
03Any agent can actYour agent calls OpenUI Cloud through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.

POLICY.TS

await arc0.policies.set('openui_cloud', {
  read: 'allow',
  write: 'ask',        // create_conversation
  destructive: 'deny',  // delete_conversation
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2

04 · AUTH AND DATA

How OpenUI Cloud connects.

Users add their OpenUI Cloud api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same OpenUI Cloud connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH: API key
CREDENTIALS: Per-tenant encrypted vault
MODEL SEES: Results only, never credentials
AUDIT LOG: Every call, on every plan

05 · WORKS WITH

Use OpenUI Cloud from any agent.

Claude

ChatGPT

Cursor

Codex

VS Code

OpenAI Agents SDK

Claude Agent SDK

Vercel AI SDK

Mastra

LangGraph

06 · RELATED

More ai and models apps.

Perplexity AI9 actions

All Images AI7 actions

AltText.ai10 actions

AltTextLab2 actions

ALL AI AND MODELS APPS →

07 · FAQ

OpenUI Cloud and Arc0, answered.

Q01

Can I use OpenUI Cloud with Claude, ChatGPT or Cursor?

Yes. Connect OpenUI Cloud to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the OpenUI Cloud actions you allow.

Q02

How do users connect OpenUI Cloud?

Users add their OpenUI Cloud api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which OpenUI Cloud actions can my agent take?

8 in total: 4 read, 3 write and 1 destructive, such as “create Conversation”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in OpenUI Cloud?

Yes. Actions like “delete Conversation” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call OpenUI Cloud too?

Yes. The same OpenUI Cloud connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug OpenUI Cloud into your agent.

Your users connect OpenUI Cloud once, under your brand. Your agent gets 8 actions behind your policies, with every call on the record.

Connect OpenUI Cloud Browse all apps →

Free to build · MCP + REST · Audit log on every plan