multimodal

About multimodal

Use multimodal with your agent

claude mcp add multimodal -- npx -y @r16t/multimodal-mcp

{
  "mcpServers": {
    "multimodal": {
      "command": "npx",
      "args": [
        "-y",
        "@r16t/multimodal-mcp"
      ]
    }
  }
}

Frequently asked questions

What is multimodal?

multimodal is an MCP (Model Context Protocol) server by rsmdt. Multi-provider media generation — images, video, audio, and transcription via a unified interface

How do I connect multimodal to Claude, Cursor, or another MCP client?

Install multimodal from its npm package (@r16t/multimodal-mcp) and register it under "mcpServers" in your client's MCP configuration — for example claude_desktop_config.json or Cursor's mcp.json — then restart the client.

Is multimodal open source?

Yes — the source code is public at github.com/rsmdt/multimodal-mcp, with 1 GitHub stars.

Can AI agents pay to use multimodal?

Not yet through Loomal — multimodal is listed as a free directory entry. If its maintainer verifies ownership, they can set per-call USDC pricing that agents pay over x402, with settlement on Base.