mcpField
S
shotflow-mcp

shotflow-mcp

Local
github.com/JOHNZhang-uiMedia & Design0Updated 17w ago

About shotflow-mcp

shotflow-mcp exposes ShotFlow storyboard and video-generation capabilities to MCP clients, including tools for tracking and revising video tasks. It also provides resources for creative types and visual styles.

Key features

  1. 01Generate storyboards from scripts or ideas
  2. 02Generate videos from storyboard shots
  3. 03Check video-generation status
  4. 04Regenerate individual shots
  5. 05List video task history and check quota
  6. 06Access creative-type and visual-style resources

Use cases

  1. 01Turning a script idea into a storyboard
  2. 02Creating a video from storyboard shots
  3. 03Checking progress or revising a generated shot
  4. 04Reviewing task history and available creative templates

MCP support

It provides seven tools and two template resources to MCP clients over Streamable HTTP. An online endpoint is available at `https://aishotflow.cn/mcp`.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"johnzhang-ui-shotflow": {
"command": "npx",
"args": [
"-y",
"shotflow-mcp-server"
],
"env": {
"SHOTFLOW_API_URL": "<SHOTFLOW_API_URL>",
"MCP_API_KEY": "<MCP_API_KEY>"
}
}
}
}
Run commandnpx -y shotflow-mcp-server
Environment variables to set
SHOTFLOW_API_URLShotFlow Express API 地址(URL 格式,例如 http://localhost:3003)
MCP_API_KEYSecretMCP Server 认证 Key(可选)

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmshotflow-mcp-server1.0.0

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

ShotFlow MCP Server

让 AI Agent 直接调用专业分镜脚本生成能力

MCP Version License Online

ShotFlow MCP Server 是 ShotFlow 的 Model Context Protocol 接口实现,让任何支持 MCP 的 AI 客户端(Claude Desktop、Cursor、Cline、VS Code Copilot 等)都能直接调用专业分镜脚本与视频生成能力。


在线使用

无需安装,直接配置 URL 即可使用:

https://aishotflow.cn/mcp

功能一览

Tool说明
generate_storyboard从剧本/创意描述生成专业分镜脚本(6种创作类型 × 7种视觉风格)
generate_video从分镜镜头生成视频(Pro 功能)
check_video_status查询视频生成状态
regenerate_shot单镜头重新生成
list_video_tasks列出视频任务历史
check_quota查询今日配额
check_health检查服务健康状态
Resource说明
shotflow://templates/creative-types6种创作类型模板与默认参数
shotflow://templates/visual-styles7种视觉风格参考与关键词

快速接入

Claude Desktop

编辑配置文件(macOS: ~/Library/Application Support/Claude/claude_desktop_config.json,Windows: %APPDATA%\Claude\claude_desktop_config.json):

{
  "mcpServers": {
    "shotflow": {
      "url": "https://aishotflow.cn/mcp"
    }
  }
}

重启 Claude Desktop,点击「Attached tools」确认 shotflow 已加载。

Cursor IDE

在项目根目录创建 .cursor/mcp.json:

{
  "mcpServers": {
    "shotflow": {
      "url": "https://aishotflow.cn/mcp"
    }
  }
}
VS Code(1.99+)

在项目根目录创建 .vscode/mcp.json:

{
  "servers": {
    "shotflow": {
      "type": "http",
      "url": "https://aishotflow.cn/mcp"
    }
  }
}
Cline / Roo-Cline

编辑 ~/.cline/mcp_settings.json:

{
  "mcpServers": {
    "shotflow": {
      "url": "https://aishotflow.cn/mcp"
    }
  }
}

调用示例

生成短视频分镜

告诉你的 AI 客户端:

用 shotflow 的 generate_storyboard 工具,帮我生成一个短视频分镜:一个创业者熬夜做产品的故事,3个场景,温情风格,9:16竖屏

AI 会自动调用 MCP Tool,返回结构化分镜结果。

查看可用创作类型

读取 shotflow 的 creative-types 资源,告诉我有哪些创作类型可选


Agent Card(A2A 协议)

其他 AI Agent 可通过以下 URL 自动发现 ShotFlow 的能力:

https://aishotflow.cn/mcp/agent-card

部署自己的实例

要求
  • Node.js 18+
  • ShotFlow Express Server 运行在 localhost:3003
安装
git clone https://github.com/YOUR_USERNAME/shotflow-mcp.git
cd shotflow-mcp
# 无需 npm install,零依赖
启动
# 开发模式
node shotflow-mcp-server.js
# 默认端口 3004

# 生产部署(systemd)
sudo cp shotflow-mcp.service /etc/systemd/system/
sudo systemctl enable shotflow-mcp
sudo systemctl start shotflow-mcp
环境变量
变量默认值说明
MCP_PORT3004MCP Server 监听端口
SHOTFLOW_API_URLhttp://localhost:3003ShotFlow Express 地址
NODE_ENVdevelopment环境模式

架构

AI Client (Claude/Cursor/...)
    ↓ Streamable HTTP (JSON-RPC 2.0)
Nginx :443
    └── /mcp → ShotFlow MCP Server :3004
                    └── HTTP → ShotFlow Express :3003
  • 协议: MCP 1.0(Streamable HTTP + SSE)
  • 传输: JSON-RPC 2.0 over HTTP
  • 依赖: 零外部依赖(纯 Node.js 实现)
  • SSE 支持: proxy_buffering off 配合 Nginx 实现流式进度推送

文件结构

shotflow-mcp/
├── shotflow-mcp-server.js   # MCP Server 主文件
├── tool-definitions.js       # 7个 Tool 的 JSON Schema 定义
├── resource-definitions.js   # 2个 Resource 定义
├── prompt-builder.js        # Prompt 构造与模型配置解析
├── package.json             # npm 包配置
├── shotflow-mcp.service     # systemd 服务文件
├── INTEGRATION.md          # 详细接入文档
├── README.md               # 本文件
└── test/
    └── test-mcp.js        # 测试套件

测试

# 启动本地服务
node shotflow-mcp-server.js &

# 运行测试
node test/test-mcp.js

相关链接


许可证

MIT License — 自由使用、修改和分发。


支持

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.