メニュー
Local MCP tools to read and visualize any file — images, video, documents, code, data, 3D, notebooks, and more — plus image tools for cropping, annotating, and extracting frames.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/QwenLM/Qwen-MM-Plugins --skill qwen-mm-plugins-coreコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Cloud MCP tools for understanding media, by model family. VL model: vision_chat (caption/VQA), ocr, grounding (detect/locate objects). Omni model (reads frames + audio together): timestamped captioning, ASR (plain / controllable / multi-speaker diarized), temporal grounding, event counting, music captioning. Plus transcribe_audio (ASR) and segmentation (SAM3). Use when a question about an image/video/audio needs an external model, not just local reading.
Web search and page extraction MCP tools (Serper, Exa, or Tavily) plus Serper Lens reverse-image search for confirming facts — web_search (find facts), web_extractor (read a page in depth), image_search (reverse-search a frame to identify an entity). Use to verify anything you cannot confirm from the media alone.
Triggered for long videos (30+ minutes), whether a single file or a directory of multiple videos. Vision-language MCP tools designed for efficient reading and semantic analysis of long videos (30+ minutes), supporting memory construction and semantic search.
SKILL.md を表示中
SOC 職業分類に基づく
| name | qwen-mm-plugins-core |
| description | Local MCP tools to read and visualize any file — images, video, documents, code, data, 3D, notebooks, and more — plus image tools for cropping, annotating, and extracting frames. |
You have qwen-mm-plugins-core MCP tools available. Use them to read and visualize any file (images, videos, documents, code, data, 3D models, notebooks, etc.) and to crop/annotate images. Prefer these MCP tools over manual scripting.
Check the qwen-mm-plugins-core tools in your tool list for full schemas and parameters.
Native reading (feeds content directly to you):
media_info. Run it before read_video and before any clip/edit — see Metadata first below.visualizeread_imageread_videosave_view (pass times=[...])Producing / annotating (writes an image file):
cropdraw_bbox| Category |
|---|
| Extensions |
|---|
| Notes |
|---|
| Documents | .pdf, .svg | Built-in (pypdfium2 + resvg) |
| Office | .docx, .pptx, .vsdx | Needs libreoffice |
| Data | .csv, .xlsx | Text table + chart image |
| Code | .js, .ts, .py, .go, .rs, .md, ... | Returns text (markdown code block) |
| Plain text | .txt, .text, .log | Returns text (fenced block) |
| Web pages | .html, .htm, .mhtml | Screenshot; needs playwright |
| Diagrams | .drawio | XML → SVG rendering |
| Subtitles | .srt, .vtt | Returns text |
| 3D Models | .obj, .stl, .glb, .gltf, .fbx, .ply, .step, .stp | Built-in; blender for best quality |
| GIS/Geo | .geojson, .kml, .shp | Built-in |
| Notebooks | .ipynb | Text cells + embedded images |
| LaTeX | .tex | Compiles to PDF; falls back to source on failure |
| Images/Videos | .jpg, .mp4, ... | Delegates to read_image/read_video |
Use pages for page ranges, budget for resolution, max_pages to cap output.
Always run media_info on a video/audio file before read_video and before any clip/trim/concat/mux — it reads only the header, so it is fast even on huge files, and it tells you how to treat the source. read_video also samples smarter once you know the fps and duration.
When juggling heterogeneous assets (action-cam clips, VFX/stock footage, voiceover, SFX), media_info is how you catch the traps that silently corrupt an edit — check for:
media_info flags it as possibly VFR. Frame-accurate cuts need a constant-fps conform first (a video-edit step) — never assume a fixed fps on VFR sources.rotation 90°/180°): the display orientation differs from stored pixels; bake it in before cropping or overlaying.media_info calls these out; both shift or break naive timestamp math.Resolution budgets: small for preview, normal (~1024) default, large for fine detail.
Video strategy: fps=0 auto-selects. Skim with fps=1, budget="normal" in 5-min chunks, then detail with fps=2, budget="large" on interesting segments. Use start_time/end_time for windowing.
Core is local-only. Cloud model/API calls live in separate capabilities — install them if you need those:
qwen-mm-plugins-api, grouped by model family: VL (vision_chat, ocr, grounding), Omni A/V (timestamped captioning, multi-speaker ASR, temporal grounding, event counting), plus transcribe_audio and segmentation. Annotate its grounding output with draw_bbox here.qwen-mm-plugins-search. Grab the frame with save_view here first.