Shotflow MCP Server

ShotFlow MCP Server — AI分镜脚本与视频生成智能体,支持生成专业分镜、视频、镜头重生成、配额查询等能力。

Local serverstdio

What is the Shotflow MCP server?

Most developer tooling work still happens through a UI a human drives. Shotflow MCP server moves it into the conversation instead. ShotFlow MCP Server — AI分镜脚本与视频生成智能体,支持生成专业分镜、视频、镜头重生成、配额查询等能力。.

The short version

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。

The tools it exposes

The server publishes 11 tools. What each one is for:

  • 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
  • MCP_PORT — 3004
  • SHOTFLOW_API_URLhttp://localhost:3003
  • NODE_ENV — development

What it needs from you

Configuration is passed through the environment: SHOTFLOW_API_URL. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Getting it running

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.

How it compares

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Shotflow's toolset — generate_storyboard, generate_video, check_video_status and 8 more — is a fair guide to whether it matches your workflow. It is maintained by JOHNZhang-ui; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 11 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Shotflow.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
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
MCP_PORT3004
SHOTFLOW_API_URLhttp://localhost:3003
NODE_ENVdevelopment

Configuration

VariableDescriptionRequired
SHOTFLOW_API_URLEndpoint or connection string the server talks to.Yes

Example prompts to try

  • Use Shotflow to generate storyboard.
  • Use Shotflow to generate video.
  • Use Shotflow to check video status.

Frequently asked questions

It connects Shotflow to MCP-compatible AI assistants such as Claude and Cursor, exposing 11 tools (generate_storyboard, generate_video, check_video_status, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Shotflow directly.