Skip to main content
Glama
apvlv

DaVinci Resolve MCP Server

by apvlv

DaVinci Resolve MCP 服务器

模型上下文协议 (MCP) 服务器,允许 MCP 客户端通过工具和资源控制并检查 DaVinci Resolve(包括 Fusion)。

它提供了什么

  • 项目管理(创建、加载、保存)

  • 时间线操作(创建时间线、切换时间线、从剪辑构建)

  • 媒体池操作(导入媒体、创建文件夹、检查文件夹)

  • Fusion 助手(向剪辑添加合成、创建节点、创建节点链)

  • Resolve 页面导航

  • 高级脚本 (execute_python, execute_lua)

Related MCP server: DaVinci MCP Professional

要求

  • Python 3.10+

  • 已启用脚本 API 的 DaVinci Resolve

  • 兼容 MCP 的客户端(例如 Claude Desktop)

安装

git clone https://github.com/apvlv/davinci-resolve-mcp.git
cd davinci-resolve-mcp
uv sync --all-extras --dev

运行服务器

uv run davinci-resolve-mcp

服务器将在启动时尝试连接到 Resolve。请确保 DaVinci Resolve 正在运行。

MCP 客户端设置

配置您的 MCP 客户端以启动服务器命令:

{
  "mcpServers": {
    "davinci-resolve": {
      "command": "uv",
      "args": ["run", "davinci-resolve-mcp"]
    }
  }
}

资源

  • system://status

  • project://current

  • project://timelines

  • timeline://current

  • mediapool://folders

  • mediapool://current

  • storage://volumes

工具

项目

  • create_project(name)

  • load_project(name)

  • save_project()

时间线

  • create_timeline(name)

  • set_current_timeline(index)

媒体

  • import_media(file_paths)

  • create_folder(name)

  • create_timeline_from_clips(name, clip_indices)

Fusion

  • add_fusion_comp_to_clip(timeline_index, track_type, track_index, item_index)

  • create_fusion_node(node_type, parameters)

  • create_fusion_node_chain(node_chain)

Resolve UI

  • open_page(page_name) 其中页面名称为以下之一:

    • media, edit, fusion, color, fairlight, deliver

高级

  • execute_python(code)

  • execute_lua(script)

开发

make install      # install deps and pre-commit hooks
make lint-check   # ruff check
make format-check # ruff format check
make test         # pytest with coverage
make check        # lint + format + tests

使用示例构思

  • “创建一个名为 My Documentary 的项目”

  • “列出当前项目中的时间线”

  • “将这些文件导入媒体池”

  • “打开调色页面”

  • “创建一个 Fusion 节点链 Blur -> ColorCorrector”

许可证

MIT (参见 LICENSE)

Install Server
A
license - permissive license
A
quality
D
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

View all related MCP servers

Related MCP Connectors

  • A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…

  • A real timeline video editor for AI agents: journaled edits, FFmpeg/MLT rendering, exports

  • Manage SRG+ hubs, channels, content, assets, users, and workspaces from any MCP-aware AI agent.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/apvlv/davinci-resolve-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server