Skip to main content
Glama
chinavideoai

chinavideoai

by gpt-img-2

China Video AI Prompt MCP

A deterministic, read-only MCP server for designing English or Chinese video prompts, reference-aware shot plans, and focused revisions. It complements ChinaVideoAI.com and does not generate media, call model providers, access accounts, compare live prices, or spend credits.

Tools

  • build_video_prompt turns a rough idea into a structured English or Chinese prompt pack.

  • plan_reference_shots creates a timed 1–6 shot sequence with reference roles and continuity anchors.

  • diagnose_video_prompt finds missing motion, camera, lighting, and continuity controls while preserving reference tokens.

  • get_china_video_resources returns canonical ChinaVideoAI.com guides and workflow pages.

All tools are deterministic and declare read-only MCP annotations. No API key is required.

Related MCP server: seevido

Install

Run directly from GitHub:

{
  "mcpServers": {
    "chinavideoai": {
      "command": "npx",
      "args": ["-y", "github:gpt-img-2/chinavideoai-prompt-mcp"]
    }
  }
}

Or clone and run locally:

pnpm install
pnpm build
node dist/index.js

Optional environment variable:

  • CHINAVIDEOAI_APP_BASE_URL: changes the resource-link origin. Defaults to https://chinavideoai.com.

Example inputs

Build a bilingual-aware prompt:

{
  "idea": "一只白鹭从清晨薄雾中的湖面起飞",
  "workflow": "image-to-video",
  "camera": "低机位缓慢跟拍",
  "referenceConstraints": "保留 @Image1 中白鹭的羽毛纹理与湖岸构图"
}

Plan reference-aware shots:

{
  "idea": "A trail shoe crosses wet rock and lands in a shallow stream",
  "shotCount": 3,
  "totalDurationSeconds": 9,
  "referenceRoles": "@Image1 controls product geometry; @Video1 controls motion timing",
  "continuityAnchor": "shoe color, laces, runner wardrobe, and travel direction"
}

OpenClaw Skill

The companion Skill is in openclaw/china-video-prompt-architect. It works as a text-only workflow without this MCP; connecting the MCP adds deterministic prompt-building and diagnostic tools.

Development

pnpm validate

This project is an independent prompt-design utility and is not official documentation or an official implementation of Seedance, Kling, Wan, MiniMax, or any other model.

License

MIT

Available Tools

4 tools
build_video_promptBuild a China AI video promptA
Read-onlyIdempotent

Turn a rough idea into a deterministic English or Chinese prompt pack with motion, camera, lighting, reference, and continuity controls. This does not generate video.

Inputs: idea (required), style, camera, motion, +7 more.

diagnose_video_promptDiagnose a video promptB
Read-onlyIdempotent

Check an English or Chinese prompt for a readable scene, visible motion, camera direction, lighting, continuity controls, and preserved reference tokens.

Inputs: prompt (required).

get_china_video_resourcesGet China AI video resourcesA
Read-onlyIdempotent

Return canonical ChinaVideoAI.com prompting, workflow, model-orientation, or safety resources. Does not fetch external content.

Inputs: topic.

plan_reference_shotsPlan a reference-aware shot sequenceA
Read-onlyIdempotent

Break one video idea into 1 to 6 timed shots with reference roles, camera direction, end frames, and continuity anchors. Read-only and deterministic.

Inputs: idea (required), shotCount, cameraStyle, referenceRoles, +2 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: diagnosing an existing prompt, building a new prompt pack, planning reference shots, and retrieving resources. No two tools could be confused for each other.

    Naming Consistency5/5

    All tool names follow the verb_noun pattern with snake_case (diagnose_video_prompt, build_video_prompt, plan_reference_shots, get_china_video_resources). The verbs and nouns are descriptive and consistent.

    Tool Count5/5

    With 4 tools, the server is well-scoped for its purpose of video prompt creation assistance. Each tool covers a distinct step in the workflow without redundancy.

    Completeness5/5

    The toolset covers the full workflow from diagnosis to building to planning, plus resource access. No obvious gaps are apparent for the stated domain of Chinese video prompting.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers