Daz Pilot

Daz Pilot

MCP server for AI-driven DAZ Studio scene editing. Runs as a native DAZ Studio plugin (DLL) and exposes all scene control, rendering, dForce, asset, and animation commands through the Model Context Protocol.

Category
访问服务器

README

DazPilot

Disclaimer: This plug‑in is not affiliated with, endorsed by, or sponsored by DAZ 3D.

MCP server for AI-driven DAZ Studio scene editing. Runs as a native DAZ Studio plugin (DLL) and exposes all scene control, rendering, dForce, asset, and animation commands through the Model Context Protocol.

How It Works

Claude Desktop  ──stdio──>  daz-mcp-client.py  ──HTTP POST /mcp──>  DazPilot (DLL inside DAZ Studio)
  • The plugin hosts an HTTP server on 127.0.0.1:8765 serving a single endpoint POST /mcp
  • Clients send JSON-RPC 2.0 messages with MCP methods: initialize, tools/list, tools/call
  • Each command maps to DAZ Studio SDK calls executed on DAZ's main thread
  • The Python shim daz-mcp-client.py translates MCP stdio transport to HTTP for Claude Desktop

196 Commands

All categories — scene, selection, properties, materials, morphs, cameras, lights, rendering, assets, animation, dForce simulation, poses, clothing, hair, environment, export, viewport, rigging, scripting, mesh queries.

Build

Prerequisites

  • CMake 3.15+
  • C++17 compiler (MSVC 2019+)
  • DAZ Studio 4.5+ SDK (place the SDK in a folder named thirdparty at the repository root; obtain it from DAZ or your own source, it is not pulled automatically)

Quick Start

cmake -B build -DDAZ_SDK_ROOT="C:\Program Files\DAZ 3D\DAZStudio4\SDK"
cmake --build build --config Release

Header-only test build (no SDK):

cmake -B build -DBUILD_TESTS=ON
cmake --build build --config Release

Install

Copy DazPilot.dll to your DAZ Studio plugins directory:

C:\Program Files\DAZ 3D\DAZStudio4\plugins\

Restart DAZ Studio. The server starts automatically on port 8765.

Direct HTTP usage

If you prefer to talk to the MCP server directly (without the Python shim), you can POST JSON‑RPC requests to the plugin’s HTTP endpoint. The server runs at http://127.0.0.1:8765/mcp and follows the JSON‑RPC 2.0 specification.

Using curl

curl -X POST http://127.0.0.1:8765/mcp \
     -H "Content-Type: application/json" \
     -d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'

The response will be a JSON object containing the list of available commands.

Using Python (requests)

import requests
payload = {"jsonrpc": "2.0", "id": 1, "method": "tools/list", "params": {}}
resp = requests.post('http://127.0.0.1:8765/mcp', json=payload)
print(resp.json())

Using JavaScript (Fetch API)

fetch('http://127.0.0.1:8765/mcp', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({ jsonrpc: '2.0', id: 1, method: 'tools/list', params: {} })
})
  .then(r => r.json())
  .then(console.log);

All other methods described in the MCP Protocol section work the same way – just replace the method and params fields. The plugin will reply with a JSON‑RPC response containing either result or error.

{
  "mcpServers": {
    "dazpilot": {
      "command": "python",
      "args": ["path/to/daz-mcp-client.py"]
    }
  }
}

The shim forwards stdio JSON-RPC to http://127.0.0.1:8765/mcp.

MCP Protocol

The plugin implements Streamable HTTP transport:

  • Endpoint: POST http://127.0.0.1:8765/mcp
  • Content-Type: application/json
  • Body: JSON-RPC 2.0 request object

Methods

Method Purpose
initialize Server capabilities & version
tools/list List all 196 commands
tools/call Execute a command

Example

{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"get_scene_info","arguments":{}}}

License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选