Topaz MCP server

RunAPI Topaz MCP Server

Topaz API access for AI agents: run image and video generation operations, poll asynchronous results, and check pricing through one focused MCP server.

Works with Claude Code, Codex, Cursor, Windsurf, VS Code, Roo Code, and any MCP-compatible host.

Install | Tools | Models | Agent Prompts | Configuration | Links

Why This Package?

@runapi.ai/topaz-mcp is a focused Model Context Protocol server for the Topaz model line on RunAPI. It gives MCP-compatible assistants direct access to 2 endpoints and 2 model variants without loading the full RunAPI catalog.

Use this per-model server when an agent should stay scoped to Topaz. Use @runapi.ai/mcp when one assistant should discover every RunAPI model line.

Install

Add it to Claude Code:

claude mcp add topaz -s user -- npx -y @runapi.ai/topaz-mcp

Use project scope when the server should be shared with a repository:

claude mcp add topaz -s project -- npx -y @runapi.ai/topaz-mcp

Codex, Cursor, Windsurf, VS Code, Roo Code, and other MCP hosts can use the same stdio command:

{
  "mcpServers": {
    "topaz": {
      "command": "npx",
      "args": ["-y", "@runapi.ai/topaz-mcp"]
    }
  }
}

checkpricing works before sign-in. For task creation and status polling, ask your assistant to call the login tool. It opens a browser login and saves credentials to ~/.config/runapi/config.json, the same file used by runapi login. Headless and CI hosts can still set RUNAPIAPI_KEY before starting the MCP host.

Ready-made examples are in examples/ for Claude, Cursor, Windsurf, VS Code, and Roo Code.

Tools

Models

Topaz covers 2 model variants across 2 endpoints. Each tool accepts the models listed for it:

Model availability can change between releases. Use check_pricing or the Topaz model page for the current catalog view.

Agent Prompts

Ask your assistant in natural language; it can inspect pricing, create the task, and return the task id plus output URLs.

Create a task

Run a Topaz upscale image task with RunAPI.

The assistant can call checkpricing, then upscaleimage, and return the task id, status, and output URLs.

Submit without waiting

Shortened. The full README is on GitHub.