Find any model or tool and jump to its page.

curl -fsSL visualsandbox.com/install.sh | sh && vsb setupOr paste the prompt into Claude Code — it installs the CLI, signs you in, and runs your first render.
Using an AI agent? Copy a setup prompt and it connects itself.
Using an AI agent? Copy a setup prompt and it connects itself.
Generate media from the editor you already have open.
Every model ships with a prompting guide. Your agent reads it before it writes.
{"mcpServers":{"visual-sandbox":{"url":"https://visualsandbox.com/mcp"}}}https://visualsandbox.com/mcpGoes in ~/.cursor/mcp.json. Sign in from Settings → MCP.
Set up Visual Sandbox (visualsandbox.com) in Cursor so you can generate images, video and audio for me.
1. Add this server to ~/.cursor/mcp.json (merge it with whatever is already there):
{"mcpServers":{"visual-sandbox":{"url":"https://visualsandbox.com/mcp"}}}
2. Open Settings → MCP, find visual-sandbox, and start the sign-in. Ask me before you approve anything on my behalf.
3. Confirm the server shows as connected. If it does not, stop and tell me what failed.
4. Do not generate anything yet. Every run costs credit, so ask me what to make, price it with estimate_cost, and wait for my yes.