piapi-mcp-server

Name: piapi-mcp-server
Author: apinetwork

@apinetwork

About piapi-mcp-server

A TypeScript implementation of a Model Context Protocol (MCP) server that integrates with PiAPI's API. PiAPI makes user able to generate media content with Midjourney/Flux/Kling/LumaLabs/Udio/Chrip/Trellis directly from Claude or any other MCP-compatible apps.

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "piapi-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli",
        "install",
        "piapi-mcp-server",
        "--client",
        "claude"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is piapi-mcp-server?

It is a TypeScript implementation of a Model Context Protocol (MCP) server that integrates with PiAPI’s API, enabling users to generate media content (images, videos, music, 3D models) directly from Claude or any other MCP-compatible app.

How to use piapi-mcp-server?

Install via Smithery (npx -y @smithery/cli install piapi-mcp-server --client claude) or manually clone the repo, run npm install and npm run build. Obtain a PiAPI API key from piapi.ai and configure the server in Claude Desktop or Cursor by adding a piapi entry in the mcpServers configuration with the PIAPI_API_KEY environment variable. After setup, send prompts for media generation.

Key features of piapi-mcp-server

Base image and video toolkits
Flux image generation from text/image prompts
Hunyuan, Skyreels, Wan video generation
MMAudio music generation from video
Kling video and effects generation
Luma Dream Machine video generation
Suno music generation
Trellis 3D model generation from image
TTS zero-shot voice generation

Use cases of piapi-mcp-server

Generate images using Flux or Midjourney (imagine) directly from chat.
Create videos with Kling, Luma, Hunyuan, Wan, or Skyreels from text or image prompts.
Produce music tracks via Suno or MMAudio from video.
Generate 3D models from images using Trellis.
Perform zero-shot voice cloning with TTS.