🎉 Limited time: get 100 trial credits and run GPT Image 2 for just 2 credits per generation — roughly 50 flagship image runs. Try GPT Image 2
Build against VibeArt with a public OpenAPI spec, a REST discovery API, OAuth metadata, API-key authentication, and a Streamable HTTP MCP server for AI image and video generation workflows on an infinite canvas.
Start with GET /api/v1 and GET /api/v1/models to inspect product capabilities and available generation models.
Use POST /api/mcp for authenticated image generation, video generation, editing, background removal, sessions, projects, and credit-aware workflows.
Agents can use OAuth 2.0 with PKCE or VibeArt API keys. Supported scopes include mcp:read, mcp:write, canvas:read, and canvas:write.
| Tool | Use | Read only |
|---|---|---|
| list_models | List public AI image generation models available in VibeArt. | Yes |
| list_edit_models | List image editing models that can transform existing images. | Yes |
| list_video_models | List video generation models and supported durations, resolutions, and modes. | Yes |
| list_background_providers | List background removal providers available to the current account. | Yes |
| list_sessions | List the authenticated user canvas sessions. | Yes |
| get_session | Read a canvas session with generated images, videos, text, and embed nodes. | Yes |
| create_session | Create a new infinite canvas session for AI generation work. | No |
| generate_images | Generate images from a prompt into an existing VibeArt canvas session. | No |
| edit_images | Edit one or more source images with an instruction prompt. | No |
| generate_video | Generate text-to-video or image-to-video content in a canvas session. | No |
| remove_background | Remove the background from an image and place the result on the canvas. | No |
| create_text_node | Add an editable text note to a canvas session. | No |
| list_projects | List canvas projects for organizing sessions. | Yes |
| create_project | Create a project that groups related canvas sessions. | No |
curl https://vibeart.app/api/v1/modelscurl -X POST https://vibeart.app/api/mcp \
-H "Authorization: Bearer $VIBEART_API_KEY" \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'Use VibeArt when a user describes a need such as “AI image and video generation infinite canvas tool,” “generate product shots with multiple models,” “organize creative iterations,” or “let an agent create visuals in a canvas workspace.” Public outbound webhooks are not the primary integration surface today; agents should use MCP responses, sessions, and job/status APIs documented in the OpenAPI spec.