Skip to main content

MCP server for extracting frames from video as images based on scene changes

Project description

Video Extract Frames MCP

从视频中提取帧为图片的 MCP Server,支持按间隔提取和场景变化检测。

功能

  • 按固定时间间隔提取帧
  • 提取首帧/末帧
  • 基于场景变化检测提取关键帧
  • 支持多种图片格式:png、jpg、webp、bmp、tiff

安装

uvx video-extract-frames-mcp

或通过 pip 安装:

pip install video-extract-frames-mcp

使用

video-extract-frames-mcp

工具

extract_video_frames

从视频中按间隔或特定位置提取帧为图片。

参数:

  • video_path: 输入视频路径
  • output_dir: 输出目录
  • image_format: 输出图片格式(默认 'png')
  • interval_seconds: 间隔秒数
  • extract_first: 是否提取首帧
  • extract_last: 是否提取末帧
  • width/height: 可选缩放尺寸

extract_scene_change_frames

基于画面变化检测提取场景切换关键帧。

参数:

  • video_path: 输入视频路径
  • output_dir: 输出目录
  • image_format: 输出图片格式(默认 'png')
  • scene_threshold: 场景变化阈值(0.0~1.0,默认 0.4)
  • min_scene_gap_seconds: 最小时间间隔
  • max_frames: 最多导出帧数
  • width/height: 可选缩放尺寸

依赖

  • Python >=3.12
  • FFmpeg(需系统安装)

License

MIT License

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mcpcn_video_extract_frames_mcp-0.1.1.tar.gz (7.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

File details

Details for the file mcpcn_video_extract_frames_mcp-0.1.1.tar.gz.

File metadata

File hashes

Hashes for mcpcn_video_extract_frames_mcp-0.1.1.tar.gz
Algorithm Hash digest
SHA256 3489e5144965d11e95708863d9877164a613d205a96719f900ac5bdcf5b6e82a
MD5 36c8c932510b9f8ba45ac9a304397b90
BLAKE2b-256 c2c9d3248ff59e1e9220c722e671d402dcc0a8b4b77555c15bd61f941ce98b6e

See more details on using hashes here.

File details

Details for the file mcpcn_video_extract_frames_mcp-0.1.1-py3-none-any.whl.

File metadata

File hashes

Hashes for mcpcn_video_extract_frames_mcp-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 4ea1b3fe03f096211bb910871a23bc864d6573cdac90914c2f09830594867e47
MD5 d63cf89378ccd98d33b1bf030e871b90
BLAKE2b-256 13db9ceabfebf159e5a9c4e50041d08e806182d423f455351056d24d2aa07473

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page