chinavideoai
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_promptturns a rough idea into a structured English or Chinese prompt pack.plan_reference_shotscreates a timed 1–6 shot sequence with reference roles and continuity anchors.diagnose_video_promptfinds missing motion, camera, lighting, and continuity controls while preserving reference tokens.get_china_video_resourcesreturns 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.jsOptional environment variable:
CHINAVIDEOAI_APP_BASE_URL: changes the resource-link origin. Defaults tohttps://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 validateThis 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 toolsbuild_video_promptBuild a China AI video promptARead-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 promptBRead-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 resourcesARead-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 sequenceARead-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
Scored across 4 tools
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.
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.
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.
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
Related MCP Connectors
Transcode, host and caption video from a prompt. Fifteen tools, nine read-only, nothing deletes.
Plan AI video shots: model picks, sourced prompts, prompting guides and real $/s costs.
Free, open source library of AI video prompts that really worked, each next to the video it produced and credited to its creator. Describe a video in plain words, in any language: your AI finds the prompts that fit by meaning, shows you the videos and can adapt the best one to your idea. Read only, with no account and no key.
Free, account-free prompt tools for ten generator types in 22 languages; no AI model execution.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables deterministic, read-only design of OpenSora video prompts and shot plans, including prompt diagnosis and access to workflow guides, without generating videos or requiring API keys.4MIT
- AlicenseAqualityDmaintenanceProvides read-only tools to build English or Chinese video prompts, plan reference-aware sequences, diagnose prompts, and fetch canonical SeeVido resources without API keys.4MIT
- AlicenseAqualityDmaintenanceEnables deterministic, read-only construction of Seedance-oriented video prompts, planning of multimodal reference-aware sequences, prompt diagnosis, and discovery of canonical See Dance 2 resources.4MIT
- AlicenseAqualityCmaintenanceA read-only, deterministic server that enables assembling copy-ready video prompts, planning timed shot sequences, diagnosing prompt clarity and current duration/resolution/reference/end-frame/audio limits, and retrieving canonical creation, guide, pricing, and policy URLs.4MIT