Skip to content
Esc
↑↓navigate↵open⌘Jpreview
On this page

MCP server

Connect AI agents and MCP-compatible clients to QuiverAI.

The QuiverAI MCP server lets compatible AI agents create SVGs, vectorize images, animate existing SVGs, inspect your Gallery, and fetch completed artwork through a secure hosted connection.

Connect your MCP client to:

https://app.quiver.ai/mcp

QuiverAI uses the remote Model Context Protocol over Streamable HTTP with OAuth. Your client starts the sign-in flow, you authorize access with your QuiverAI account, and the client receives a token scoped to your account.

What agents can do

Once connected, agents can:

  • List the QuiverAI models available to your account with list_models.
  • Browse Gallery metadata with list_creations and fetch selected creation metadata or SVG content with get_creation and get_creation_content.
  • Request a PNG preview alongside SVG content when they need to show a creation in chat.
  • Create text-to-SVG generation tasks with create_generation.
  • Pass image and SVG sources directly to create tools as public URLs, base64 payloads, or completed Quiver upload IDs. Quiver fetches or decodes non-upload sources, validates them, stores them, and persists upload IDs in the task.
  • Vectorize raster image sources with create_vectorization.
  • Animate an existing SVG creation or SVG source with create_animation (coming soon).
  • Poll generation, vectorization, and animation tasks with get_task until output is complete.

Setup

Use the hosted endpoint directly in clients that support remote MCP servers.

Add QuiverAI from the CLI:

codex mcp add quiverai --url https://app.quiver.ai/mcp

Then run the login flow when Codex prompts you, or start it manually:

codex mcp login quiverai

Add QuiverAI as an HTTP MCP server:

claude mcp add --transport http quiverai https://app.quiver.ai/mcp

Open a Claude Code session and run /mcp to complete authentication.

Add QuiverAI to your Cursor MCP configuration:

{
  "mcpServers": {
    "quiverai": {
      "url": "https://app.quiver.ai/mcp"
    }
  }
}

After saving the config, use Cursor’s MCP tools UI or command palette to connect and complete the OAuth flow.

For clients with native remote MCP support, add https://app.quiver.ai/mcp as a Streamable HTTP server.

For clients that only support stdio MCP servers, use mcp-remote:

{
  "mcpServers": {
    "quiverai": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://app.quiver.ai/mcp"]
    }
  }
}

Permissions

The MCP server uses scoped OAuth access:

  • Read access lets agents list models, inspect Gallery items, read artwork content, and poll tasks.
  • Write access lets agents start text-to-SVG generations, vectorizations, and animations. The MCP server does not expose a separate upload-slot tool; sources are supplied inline to create tools or referenced by an existing completed upload ID.

MCP is a Platform product surface. MCP task creation follows Platform billing: eligible weekly app credits are used first, and prepaid on-demand credits can cover additional work. Public API calls use API prepaid balance; see API Pricing.

Animations (coming soon)

Use create_animation to animate an existing QuiverAI creation or SVG source. Supply exactly one source:

  • { "creationId": "..." } for an existing SVG creation in your Gallery.
  • { "url": "https://..." } for a public SVG URL.
  • { "base64": "...", "mediaType": "image/svg+xml" } for an inline SVG payload.
  • { "uploadId": "..." } for an existing completed Quiver upload.

The tool returns a taskId. Poll that task with get_task until it completes, then read the resulting creation with get_creation_content.

Reading creation previews

Use get_creation_content when your client needs the SVG for a specific creation. By default the tool returns SVG content only.

When the client should render the creation visually in chat, set includePng: true. QuiverAI returns the SVG together with a PNG preview and a render instruction so the client can display the image directly to the user without rasterizing the SVG itself.

Troubleshooting

If connection fails, verify that your client supports remote MCP over Streamable HTTP or use the mcp-remote fallback shown above. If authentication opens in the browser but does not return to the client, remove the saved MCP connection from your client and add it again.

For account issues, contact us.

Was this page helpful?