LABSCO SUMMARY

Many generative models, one key.

The appeal is breadth without integration work: image, video, music and 3D across a dozen named models, all behind a single PiAPI key. The contract-backed tools are the interesting engineering — a tool exists for every committed model-and-task pairing, and a drift detector keeps that surface aligned with PiAPI's catalog as it changes. The practical caveat is timeouts: video and other heavy jobs can outrun a client's default limit, so budget for that when wiring it up.

What it is

A TypeScript MCP server that fronts PiAPI's media-generation API, so an assistant can create images, video, music and 3D models directly. It ships hand-written convenience tools plus a contract-backed tool for every committed PiAPI model-and-task pairing, kept in sync with PiAPI's versioned catalog by a drift detector.

What you get

Image generation from text or image prompts with Flux, and Midjourney imagine
Video generation from text or image prompts — Hunyuan, Skyreels, Wan, Kling and Luma Dream Machine
Music generation with Suno, and MMAudio music from video, plus zero-shot TTS voice generation
3D model generation from an image with Trellis
A contract-backed tool per committed PiAPI capability, named piapi_<model>_<task_type>, generated from the committed catalog
A drift detector that diffs the catalog against PiAPI Manager's versioned contract to flag new, deprecated or changed APIs

Requirements

A PiAPI API key in PIAPI_API_KEY, from the PiAPI workspace. Node.js 16.x or higher. Clone, then npm install and npm run build, which produces dist/index.js for the client to launch with node. The package.json names it piapi-mcp-server at 1.0.0. The README warns that time-consuming jobs like video generation may not finish within a client's timeout — the MCP Inspector, for instance, defaults to 10 seconds, which it suggests raising for generation tasks.

Setup effort

Build from source

See installation options

USE CASES

01

Generating an image from a description

Send a text or image prompt to Flux or Midjourney imagine and get a picture back in the conversation.

02

Making a short video

Drive one of the video models — Hunyuan, Kling, Luma and others — from a text or image prompt, allowing for the longer run time.

03

Producing music or a voice clip

Generate a track with Suno, score a video with MMAudio, or synthesise speech with zero-shot TTS.

04

Turning an image into a 3D model

Pass an image to Trellis for 3D model generation.

BEFORE YOU INSTALL

What to know first

Requires

Node.js 16 or later
PIAPI_API_KEY in your environment

Where it runs

Both documented clients run the server on your machine.

INSTALLATION

Connect your client

MCP Clients

Claude Desktop, Cursor

JSON

{
  "mcpServers": {
    "piapi": {
      "command": "node",
      "args": [
        "<YOUR_PATH_TO_PIAPI_MCP_SERVER>/dist/index.js"
      ],
      "env": {
        "PIAPI_API_KEY": "<YOUR_PIAPI_API_KEY>"
      }
    }
  }
}

PiAPI