一个确定性的、只读的 MCP 服务器，用于设计视频提示词和分镜方案。它是对 OpenSora2.com 上独立资源的补充，不生成视频、不调用模型提供商、不访问账户，也不消耗积分。
build_video_prompt 将粗略的想法转化为结构化的提示词包。
plan_shots 创建带连续性锚点的 1–6 镜头定时序列。
diagnose_prompt 找出缺失的运动、镜头、灯光和连续性控制。
get_resources 返回权威的 OpenSora2.com 指南和工作流页面。
所有工具都是确定性的，并声明了只读 MCP 注解。无需 API 密钥。
Related MCP server: Enhanced Multimedia Analysis MCP
直接从 GitHub 运行：
{
"mcpServers": {
"opensora2": {
"command": "npx",
"args": ["-y", "github:gpt-img-2/opensora2-prompt-mcp"]
}
}
}或克隆后在本地运行：
pnpm install
pnpm build
node dist/index.js可选的环境变量：
OPENSORA2_APP_BASE_URL：更改资源链接的来源。默认为 https://opensora2.com。
构建提示词：
{
"idea": "A red ceramic teapot steams on a rain-streaked cafe window",
"workflow": "image-to-video",
"camera": "slow 10 cm push-in",
"motion": "steam curls upward while raindrops slide down the glass",
"referenceConstraints": "teapot silhouette, glaze pattern, and window composition"
}规划镜头：
{
"idea": "A trail shoe crosses wet rock and lands in a shallow stream",
"shotCount": 3,
"totalDurationSeconds": 9,
"continuityAnchor": "shoe color, laces, runner wardrobe, and travel direction"
}配套技能位于 openclaw/opensora-video-prompt-architect。它可以在不连接此 MCP 的情况下作为纯文本工作流使用；连接 MCP 后，将增加确定性的提示词构建和诊断工具。
pnpm validate
pnpm test:smoke本项目是一个独立的提示词设计工具，并非官方 Open-Sora 项目或官方模型实现。
MIT
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Find your AI agent's likely failure mode, get runtime settings, and clarify ambiguous prompts.
Build and run visual creative-production workflows from your AI agent.
Generate logos, social posts, app screenshots, comic panels & visual-novel assets from prompts.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/gpt-img-2/opensora2-prompt-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server