Manage captions/subtitles through an SRT-like, time-ordered Card model. To inspect caption text content, use the `read_captions` tool; legacy projects may persist a one-time derived-caption reconciliation before returning the read. # When to read first - Card-targeted actions (`…
jsonstringJSON for split_card after read_captions {"words":true}: {"cardId":"<cardId>","beforeWordKey":"<token-id>","revision":"..."}; for three or more Cards pass every boundary at once: {"cardId":"<cardId>","beforeWordKeys":["<token-a>","<token-b>"],"revision":"..."}. JSON for merge_car…
listbooleanFor action="track", list available source tracks instead of changing the captions source association.
actionRequiredstringOne of: enable, disable, refresh, reset, set_card_text, set_card_tokens, set_card_style, set_card_span_style, set_card_layout, set_max_characters, split_card, merge_cards, reset_card, resegment_cards, cue_override, cue_reset, template, translate, style, layout, layout_policy, po…
presetstringFor action="enable": optional built-in caption preset id/name. Omit or pass "auto" for the default Plain visual style. For action="template": legacy alias for templatePreset; prefer templatePreset so it is not confused with enable presets, layout json preset, or USER-saved prese…
trackIdstringTrack alias (V1, A1) or ID for action="track" only. Do not pass this to action="enable"; to choose what captions visibly read from, use action="set_sources" with json like {"sources":[{"trackId":"A1"}]}.
projectIdstringExisting project ID from the editor URL or list_projects. Pass this when continuing work on an existing project and the external MCP session is not already targeted.
trackOrderInternal 0-based track order for action="track" only. Do not pass this to action="enable"; prefer user-facing trackId aliases like "V1", "V2", or "A1" after action="track" with list=true returns the exact order.
captionsItemIdstringCaptions item id (or short prefix) returned by read_captions. When provided, scopes style / layout / template / preset / source-track writes directly to that captions layer, bypassing default track-scoped lookup. For destructive reset, it chooses the visual/source settings to re…
templatePresetstringFor action="template" only: built-in caption preset id/name. Omit to list the language-aware recommendation catalog with styleProfile (actual visual behavior, excluding font size/position) and paginationProfile (preset-owned wordsPerPage pacing only); pass a returned id/name to…
No reviewed structured output summary is available.
OAuth connection. Risk level 2 of 5.
Free Action
No published Skills explicitly reference this Action yet.