What dependencies does the server need?
It requires an OpenAI API key and base URL, set via the environment variables `OPENAI_API_KEY` and `OPENAI_BASE_URL`. No additional external services are needed.
@nifengxiaofei
基本情報
概要はまだありません
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"mcp-server-3Dpicture": {
"command": "node",
"args": [
" mcp-server-3Dpicture/build/index.js"
],
"env": {
"OPENAI_API_KEY": "xxx",
"OPENAI_BASE_URL": "xxx"
},
"toolCallTimeoutMillis": 180000
}
}
}url: The picture url send to tool, Required
It is a TypeScript-based MCP server that converts a 2D image of people into a 3D picture. It uses an OpenAI API to generate the 3D effect and optionally adds a text caption under the photo frame.
Install dependencies with npm install, build with npm run build, then configure the server in your MCP client (e.g., Cursor) by adding an entry to ~/.cursor/mcp.json with the node command, the build path, and the required OPENAI_API_KEY and OPENAI_BASE_URL environment variables. The server exposes a tool called generate_3Dpicture that accepts a required url (the image URL) and an optional text (caption).
generate_3Dpicture for 2D‑to‑3D conversionIt requires an OpenAI API key and base URL, set via the environment variables `OPENAI_API_KEY` and `OPENAI_BASE_URL`. No additional external services are needed.
On macOS, the configuration file is located at `~/.cursor/mcp.json`. You must add an entry with the `command`, `args`, and `env` fields as shown in the README.
Yes, the tool has a configurable timeout; the example uses `toolCallTimeoutMillis: 180000` (3 minutes) to allow enough time for the 3D generation.
You can use the MCP Inspector by running `npm run inspector`, which provides a URL for debugging the server over stdio.
It requires a `url` (the picture URL) and accepts an optional `text` for a caption under the photo frame.

Drive Veltake Studio from any AI agent: create film and ad projects, have the Studio agent build scenes on the canvas, price and start renders, export edited cuts, and make single images, video, speech and music in one c
Generate and edit images with GPT Image 2.5 for $0.029 each. A free you.bot key (not an OpenAI key) comes with 50 credits — about 17 images — and needs no credit card.

A library of conversion components for e-commerce, built on A/B tested mechanics and handed straight to your coding agent. 65 pieces drawn from mechanics that have been A/B tested in real stores: cart drawer with the ups

diggercamp finds independent music by how it sounds. Paste any Bandcamp, YouTube or SoundCloud link and get the closest sonic matches from 4M+ independent tracks — matched by rhythm, timbre, key and energy, not genre tag
Generate images, videos, music, and voice-overs directly from your AI agent. The full Artlist AI creative suite as an MCP server — works with Claude, ChatGPT, and VS Code, with more platforms coming soon.
コメント