WaveSpeed MCP server

WaveSpeed MCP Server

<!-- mcp-name: ai.wavespeed/mcp -->

An MCP server for the WaveSpeed platform: run any model on the live catalog — image, video, audio, 3D — from Claude Code, Claude Desktop, Cursor, Cline, or any MCP client.

Built on the same design as the open-source @wavespeed/cli:

• No hardcoded models. The catalog comes from the live API (1h cache); new platform models work the day they ship.
• One generation verb. runmodel executes anything; getmodel_schema tells the agent what inputs a model actually accepts, so it reads before it writes.
• Inputs are never mutated. The one explicit transform is the @path marker — a "@./photo.jpg" value inside input uploads the file and substitutes its hosted URL. Bare paths are passed through untouched.
• Honest pricing. getprice quotes before you spend and names the inputs the quote was blind to (unpricedinputs) instead of presenting a formula's floor as "the" price.

Tools

If runmodel hits its wait limit the task keeps running server-side — the error names the prediction id, and getprediction picks it up.

Setup

Auth resolves from WAVESPEEDAPIKEY, or from the CLI's stored login (wavespeed login) — one login covers both tools. Keys: wavespeed.ai/accesskey.

Claude Code

claude mcp add wavespeed -- npx -y @wavespeed/mcp

Claude Desktop / other clients (mcpServers config):

{
  "mcpServers": {
    "wavespeed": {
      "command": "npx",
      "args": ["-y", "@wavespeed/mcp"],
      "env": { "WAVESPEED_API_KEY": "wsk_..." }
    }
  }
}

Example prompts

• "Generate a 16:9 hero image of a cyberpunk skyline at golden hour."
• "Take ./photo.jpg and replace the background with a sunlit kitchen." (the agent passes "@./photo.jpg")
• "Animate ./hero.png with subtle parallax — check the price first."

Development

npm install
npm run dev        # run from source (stdio)
npm run lint       # typecheck
npm run build      # tsc → dist/

License

MIT

WaveSpeed AI — AI image & video generation platform. Try it in the browser: Image generator · Video generator