studio-mcp
Enables LLM agents to orchestrate a film production pipeline from brief to final cut, including shot planning, rendering, quality control, and assembly, using block-method planning and style-drift QC.
README
studio-mcp
The block-method film pipeline as agent-callable MCP tools.
An MCP server that lets an LLM agent drive a full brief → shots → render → QC → cut
workflow by calling tools — instead of clicking through generation UIs by hand.
Plan-then-generate, never reverse: every shot is planned (type, move, duration)
before any pixel is made, and every still is QC'd against a locked look so the
piece stays on-model.
Why
Single-tool MCP servers (one model, one call) are common. This is the layer above: it orchestrates across your generation stack with a block-method planner and a style-drift QC gate — the part nobody ships.
Tools (v1)
| Tool | What it does |
|---|---|
plan_shots(brief, project, n_shots) |
brief → structured shot plan (type · camera move · duration · action) |
lock_campaign(project, aspect, stock, hex_palette, elements, audio) |
lock the look so every shot stays on-model |
qc_still(project, image, shot_id, threshold) |
vision style-drift QC — scores a still vs shot intent + locked look, pass/fail + fix |
assemble(project, clips) |
cut manifest — shot order, durations, audio/lip-sync notes |
project_status(project) |
what stages exist for a project |
v1.1 (render phase, via Higgsfield CLI):
train_character (soul-id self-clone) · gen_still (Soul) · animate (Seedance/Kling).
Provider-agnostic
The LLM layer talks to any OpenAI-compatible endpoint — Anthropic, OpenRouter, OpenAI, or a local server — chosen entirely through env config. No provider is hard-coded.
cp .env.example .env # set STUDIO_LLM_BASE_URL / _MODEL / _API_KEY
Install
python3 -m venv .venv && source .venv/bin/activate
pip install -e .
Run
studio-mcp # stdio MCP server
Register with an MCP client (e.g. Claude Code / Claude Desktop):
{
"mcpServers": {
"studio": {
"command": "/path/to/studio-mcp/.venv/bin/studio-mcp",
"env": { "STUDIO_LLM_API_KEY": "sk-..." }
}
}
}
Example flow
plan_shots("MARÉA — wordless coastal slow-burn, 90s", project="marea")
lock_campaign("marea", aspect="2.39:1", stock="Kodak 500T, soft handheld",
hex_palette=["#1b2a3a","#c8a15a"], elements=["the woman in grey"],
audio="diegetic SFX only, no music")
# render a still (v1.1) → then:
qc_still("marea", image="assets/shot1.png", shot_id=1) # pass/fail + fix
assemble("marea") # cut manifest
State lives under STUDIO_ROOT (default ~/studio-projects/<project>/) as plain
JSON — human-inspectable, and a clean contract a future console can read.
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。