MCP server

Connect AI agents and MCP-compatible clients to QuiverAI.

The QuiverAI MCP server lets compatible AI agents create SVGs, vectorize images, inspect your Gallery, and fetch completed SVG content 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: each creation’s ID, path, prompt and icon set ID, never its SVG. Fetch selected creation metadata or SVG content with get_creation and get_creation_content.
• Page through list_creations with cursor and limit (1–100 creations; each icon in an icon set counts as one, and a page can end inside a set). Group icons by iconSetId.
• 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; set n from 1 to 16 when you need multiple outputs (the default is 1).
• Pass image and SVG sources directly to create tools as public URLs, base64 payloads, or completed QuiverAI upload IDs. QuiverAI fetches or decodes non-upload sources, validates them, stores them, and persists upload IDs in the task. URL and base64 sources may include an optional filename.
• Vectorize raster image sources with create_vectorization.
• Animate an existing SVG creation or SVG source with create_animation.
• Edit an existing SVG creation or SVG source from an instruction with create_edit; pass up to 4 optional image references to guide the change. The edit is saved as a new creation; a creation ID source is not changed.
• Successful create calls wait for completion and return status: "completed", the chatId the create ran in, completed creationIds, and the versions each write committed (artifactId, versionId, path). Fetch those creations directly with get_creation_content.

Models and completion

Call list_models before choosing a model. The response is the source of truth for the model and operations available to the connected App account. MCP create tools currently accept the returned Arrow 2 model only; inspect its account-level access and operation-level availability before a paid create. Do not substitute a model from the API Platform catalog.

A successful create response is already complete. Pass each returned creationId directly to get_creation_content; a chatId is not a creation ID. Use get_task with the returned chatId only when you need to inspect the Chat’s current creations later. Do not submit another paid create call to check progress or retry a failed create automatically.

Setup

Choose an installer below. Cursor and Visual Studio Code open an install confirmation.

Install in CursorInstall in VS Code

Manual setup

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

codex mcp login quiverai

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

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

{
  "servers": {
    "quiverai": {
      "type": "http",
      "url": "https://app.quiver.ai/mcp"
    }
  }
}

{
  "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 creation content, and inspect existing tasks.
• Write access lets agents start text-to-SVG generations, vectorizations, animations, and edits. 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 an App product surface. MCP task creation counts toward the eligible weekly App usage allowance first, then toward prepaid App usage. Public API calls use the API Platform prepaid balance; see API Pricing.

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.