BlitzReels Video Editor
Server Details
Create, edit, reframe, caption, organize, generate, and export short-form videos with BlitzReels.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 151 tools
Many tools overlap heavily within clusters: carousels_board_edit already inserts/duplicates/moves/removes slides and sets themes, yet carousels_slides_insert, carousels_slides_reorder, carousels_slides_remove, carousels_apply_theme and carousels_board_version_restore exist separately, and carousels_get/board_get plus carousels_compile/patch_slide have unclear boundaries. Timeline editing is split across update_timeline_clip, batch_update_timeline_clips, editor_items_move, editor_items_remove, delete_timeline_items, timeline_trim_apply and timeline_split_apply, and asset placement across timeline_media_add, timeline_audio_add and editor_assets_insert, so an agent can plausibly pick the wrong path for the same outcome.
Most names are snake_case, but the prefix convention flips: noun-first namespace style (carousels_board_edit, media_assets_get, projects_create, workspace_context_get) coexists with bare verb-first names (add_text_overlay, add_transition, mute_clip_audio, batch_update_timeline_clips, delete_timeline_items). Singular/plural namespaces are also inconsistent (clips_get vs clip_share_get, media_assets_get vs media_list), though names remain readable.
151 tools is an extreme surface for a video editor, far beyond what an agent can reason over reliably, and the volume is inflated by redundant near-duplicates (six upload/import tools, three clip status readers, dozens of carousel tools). The scope is real, but the tool-per-operation decomposition is disproportionate.
The surface covers nearly the full lifecycle: workspaces/brand context, media import and inspection, projects, timeline assembly, captions, carousels, AI generation, storyboards, publishing, exports, analytics and learning. Gaps are minor (no project delete/rename, limited project-level settings update), and agents can work around them with existing tools.
Available Tools
151 toolsadd_text_overlayAdd Title CardCIdempotentInspect
Add an opening title card (hook) or generic text overlay to a project timeline. Defaults to classic white: black text on a white card.
Inputs: text (required), projectId (required), idempotencyKey (required), kind, +7 more. Returns: txid, result, replayed, revision, +8 more
add_transitionAdd TransitionCIdempotentInspect
Add a timed transition effect, optionally attached to one timeline item and paired with sound.
Inputs: projectId (required), startSeconds (required), idempotencyKey (required), name, +8 more. Returns: txid, result, replayed, revision, +8 more
batch_update_timeline_clipsBatch Update Timeline ClipsADestructiveIdempotentInspect
Update timing, trim, layer, or state for up to 100 timeline items in one sequence transaction.
Inputs: updates (required), projectId (required), idempotencyKey (required), expectedRevision. Returns: txid, result, replayed, revision, +8 more
captions_look_applyApply Caption LookADestructiveIdempotentInspect
Apply a verified caption look to one project. Preserves word overrides unless clearWordOverrides=true. Existing captions are restyled; spoken audio is preserved.
Inputs: lookId (required), projectId (required), idempotencyKey (required), workspaceId, +1 more. Returns: object
captions_source_preparePrepare Source CaptionsADestructiveIdempotentInspect
Restore editable project captions from the selected source's completed canonical transcript. Keeps the full recording and avoids duplicate captions on identical retries. Requires source transcription first; no-speech is an explicit successful state.
Inputs: assetId (required), projectId (required), workspaceId (required), idempotencyKey (required). Returns: object
captions_themes_listList Caption ThemesARead-onlyIdempotentInspect
List built-in caption looks and saved caption themes available to a workspace.
Inputs: workspaceId, includeSavedThemes, includeBuiltInLooks. Returns: themes
captions_words_correctCorrect Caption WordsADestructiveIdempotentInspect
Replace selected caption words by their stable IDs. Preserves timing and the other captions; this does not change the spoken audio.
Inputs: updates (required), projectId (required), workspaceId (required), idempotencyKey (required). Returns: object
captions_words_listRead Caption WordsARead-onlyIdempotentInspect
Read bounded editable caption words and stable word IDs for one project, optionally matching text.
Inputs: limit (required), offset (required), matchText (required), projectId (required), +1 more. Returns: object
carousels_apply_brandCarousel apply brandCDestructiveIdempotentInspect
Replace this carousel's styling with the workspace's saved brand theme.
Inputs: projectId (required), idempotencyKey (required), workspaceId. Returns: kit, name, frame, style, +11 more
carousels_apply_templateCarousel apply templateCDestructiveIdempotentInspect
Replace one carousel slide with a saved private template.
Inputs: projectId (required), slideIndex (required), idempotencyKey (required), savedTemplateId (required), +1 more. Returns: kit, name, frame, style, +11 more
carousels_apply_themeCarousel apply themeCDestructiveIdempotentInspect
Replace this carousel's styling with an existing saved theme.
Inputs: themeId (required), projectId (required), idempotencyKey (required), workspaceId. Returns: kit, name, frame, style, +11 more
carousels_board_editEdit Carousel BoardADestructiveIdempotentInspect
Apply ordered operations to a carousel board by slide and element ID: add a slide from a template with its text and photos, change text and style, insert, duplicate, move or remove slides, set the theme, apply the brand or a saved theme, hide or lock an element. Operations apply to the latest board unless expectedRevision is set; dryRun saves nothing. Returns the base and new revision, affected IDs, slide order and a summary of each changed slide; errors name the failing operation. Identical idempotency keys replay.
Inputs: projectId (required), operations (required), idempotencyKey (required), dryRun, +2 more. Returns: object
carousels_board_generateGenerate CarouselADestructiveIdempotentInspect
Write and design a full carousel from a prompt into the project board: hook, body slides, ending call to action and a post caption, styled with the brand kit or a preset style, with optional AI photos (photos finish in the background; pendingAssetIds lists them). Replaces the current board and renames the project. Uses AI and image credits; a retry with the same idempotency key and input replays the first result without generating or charging again.
Inputs: goal (required), style (required), places (required), prompt (required), +9 more. Returns: object
carousels_board_getGet Carousel BoardARead-onlyIdempotentInspect
Read a carousel board: revision, caption, pending AI images and a summary of every slide with its elements in paint order (ID, type, parent, text, image source, box in slide pixels, font, color, hidden, locked), plus the brand theme and saved themes. carousels_board_edit targets these IDs and theme ids. view full adds the board composition (editor element model; colors may be brand tokens like var(--br-accent); media sources are asset:, brand:logo or bundled paths). slideIds limits the summary to those slides.
Inputs: view (required), slideIds (required), projectId (required), workspaceId. Returns: object
carousels_board_ideasRecommend Carousel IdeasARead-onlyIdempotentInspect
Recommend six carousel ideas from the workspace brand brief, each with a cover hook, angle, goal (grow, convert or both), archetype and why it should perform. Pass one to carousels_board_generate as its prompt.
Inputs: workspaceId. Returns: object
carousels_board_imageGenerate Carousel PhotoAInspect
Start one AI photo shaped for the board (slide or square) and return its asset: source. The image finishes in the background; place it with carousels_board_edit right away, it appears once ready. Uses image credits.
Inputs: shape (required), prompt (required), projectId (required), workspaceId. Returns: object
carousels_board_templatesList Carousel Board TemplatesARead-onlyIdempotentInspect
List carousel slide templates: id, family, label and slots (key, kind text or image, sample). carousels_board_edit insertTemplateSlide takes a template id and slot values.
Inputs: workspaceId. Returns: object
carousels_board_version_restoreRestore Carousel Board VersionADestructiveIdempotentInspect
Replace a carousel board with a saved version from carousels_board_versions as a new revision; every version stays in the history, so a restore can itself be undone by restoring another. Replaces the latest board unless expectedRevision is set. Identical idempotency keys replay.
Inputs: projectId (required), versionId (required), idempotencyKey (required), expectedRevision (required), +1 more. Returns: object
carousels_board_versionsList Carousel Board VersionsARead-onlyIdempotentInspect
List saved versions of a carousel board, newest first (revision, source: baseline, editor, agent, api, generation or restore; author, merged change count, slide count), or with versionId read one version as a board summary. Saves by the same author and source within three minutes share one version; the newest 50 are kept.
Inputs: view (required), limit (required), projectId (required), versionId (required), +1 more. Returns: object
carousels_cloneClone CarouselCIdempotentInspect
Duplicate a carousel onto a new project. Copies slots. Icon and shot values may be pack filenames or asset:<media_asset_id>.
Inputs: projectId (required), idempotencyKey (required), name, workspaceId. Returns: kit, name, frame, style, +11 more
carousels_compileCompile CarouselCDestructiveIdempotentInspect
Create or replace a carousel project from a slide document. Server owns chip layout, safezones, and exact export pixels.
Inputs: name (required), slides (required), platform (required), idempotencyKey (required), +6 more. Returns: frame, job_id, slides, platform, +7 more
carousels_delete_templateCarousel delete templateBDestructiveIdempotentInspect
Delete one saved private carousel slide template.
Inputs: projectId (required), idempotencyKey (required), savedTemplateId (required), workspaceId. Returns: kit, name, frame, style, +11 more
carousels_delete_themeCarousel delete themeCDestructiveIdempotentInspect
Delete one saved private carousel theme.
Inputs: themeId (required), projectId (required), idempotencyKey (required), workspaceId. Returns: kit, name, frame, style, +11 more
carousels_expand_recipeExpand Carousel RecipeBRead-onlyIdempotentInspect
Turn a named recipe or a brief into compile-ready named-template slides. Expand never publishes and never invents metrics.
Inputs: recipeId (required), name, brief, offer, +5 more. Returns: name, locale, slides, platform, +1 more
carousels_getGet Carousel DocumentCRead-onlyIdempotentInspect
Read the carousel slot document and the named template catalog.
Inputs: projectId (required), workspaceId. Returns: kit, name, frame, style, +10 more
carousels_migrateMigrate Legacy CarouselBDestructiveIdempotentInspect
Rebuild a compile slot document from a legacy overlay carousel. Then patch slots like any compiled deck.
Inputs: projectId (required), idempotencyKey (required), workspaceId. Returns: kit, name, frame, style, +11 more
carousels_patch_slidePatch Carousel SlideCDestructiveIdempotentInspect
Patch native slots/media or select a completed Remotion frame artifact and crop. Requires expectedRevision; identical keys replay.
Inputs: projectId (required), slideIndex (required), idempotencyKey (required), expectedRevision (required), +7 more. Returns: kit, name, txid, frame, +12 more
carousels_previewPreview CarouselBDestructiveIdempotentInspect
Render and store private JPEG previews for the selected carousel slides. Replaces cached previews at deterministic storage keys; preserves the source project and slide document.
Inputs: chrome (required), projectId (required), idempotencyKey (required), workspaceId, +1 more. Returns: frame, slides, platform, revision, +3 more
carousels_save_templateCarousel save templateBDestructiveIdempotentInspect
Save one carousel slide as a private template; removes the oldest saved template when the 40-template limit is reached.
Inputs: name (required), projectId (required), slideIndex (required), idempotencyKey (required), +2 more. Returns: kit, name, frame, style, +11 more
carousels_save_themeCarousel save themeBDestructiveIdempotentInspect
Save and activate the current carousel styling as a private theme; removes the oldest saved theme when the 40-theme limit is reached.
Inputs: name (required), projectId (required), idempotencyKey (required), scope, +1 more. Returns: kit, name, frame, style, +11 more
carousels_slides_insertCarousel Slides insertAIdempotentInspect
Insert one new carousel slide from a named template or copy an existing slide. Preserves existing slide content.
Inputs: index (required), projectId (required), idempotencyKey (required), templateId, +2 more. Returns: kit, name, txid, frame, +12 more
carousels_slides_removeCarousel Slides removeCDestructiveIdempotentInspect
Remove one carousel slide and its content from the project.
Inputs: index (required), projectId (required), idempotencyKey (required), workspaceId. Returns: kit, name, txid, frame, +12 more
carousels_slides_reorderCarousel Slides reorderCDestructiveIdempotentInspect
Move one carousel slide to a new index. Replaces the existing slide order.
Inputs: to (required), from (required), projectId (required), idempotencyKey (required), +1 more. Returns: kit, name, txid, frame, +12 more
carousels_slides_undoCarousel Slides undoCDestructiveIdempotentInspect
Restore the previous carousel document revision, replacing the current slide document.
Inputs: projectId (required), idempotencyKey (required), workspaceId. Returns: kit, name, txid, frame, +12 more
characters_applyApply Reusable CharacterCDestructiveIdempotentInspect
Create or update a reference-based character for repeatable faceless story generation.
Inputs: name (required), idempotencyKey (required), type, species, +10 more. Returns: character, mutationReceipt
characters_getGet Reusable CharacterARead-onlyIdempotentInspect
Inspect one reusable character and its ordered reference-image set before planning a story.
Inputs: characterId (required), workspaceId. Returns: character
characters_listList Reusable CharactersARead-onlyIdempotentInspect
List bounded reusable characters with identity, voice, facts, and image-reference metadata.
Inputs: limit, offset, workspaceId, includeArchived. Returns: bounds, characters
clip_batches_deleteDelete Clip BatchADestructiveIdempotentInspect
Preview or delete a terminal clip batch. Dry-run is the default; real deletion requires explicit confirmation, retention choice, workspace delete permission, and an idempotency key.
Inputs: batchId (required), idempotencyKey (required), dryRun, retention, +2 more. Returns: object
clips_candidates_listReview Clip CandidatesARead-onlyIdempotentInspect
Read existing suggested moments with source ranges, hooks, transcript excerpts and thumbnails before producing videos. Results are bounded; this does not generate suggestions or render clips.
Inputs: limit (required), offset (required), assetId (required), workspaceId (required). Returns: object
clips_createCreate ClipsBDestructiveInspect
Create a private BlitzReels clip batch from an existing asset or a user-provided video URL. Supports public social videos, Google Drive, and direct media URLs.
Inputs: url, assetId, seriesId, clipCount, +9 more. Returns: batch, result
clips_delivery_promotePromote Reviewed Clip ExportADestructiveIdempotentInspect
Make one completed export the accepted delivery for a clip after explicit visual-QA confirmation. Replaces the delivery pointer and preserves earlier exports.
Inputs: clipId (required), exportId (required), idempotencyKey (required), confirmVisualQa (required), +1 more. Returns: object
clips_exportExport One ClipBDestructiveIdempotentInspect
Render one managed clip at an existing-account-supported quality. Returns persisted export state; inspect until the accepted delivery file is ready. Can spend existing account credits.
Inputs: clipId (required), idempotencyKey (required), format, resolution, +2 more. Returns: object
clips_getGet Clip BatchBRead-onlyIdempotentInspect
Get status, generated clips, render counts, and download links for a BlitzReels clip batch.
Inputs: batchId (required), workspaceId. Returns: batch
clips_inspectInspect One ClipBRead-onlyIdempotentInspect
Read one managed clip's selected source range, project, workflow state and delivery information.
Inputs: clipId (required), workspaceId. Returns: object
clips_listList ClipsBRead-onlyIdempotentInspect
List bounded managed clips from the selected source or project with their current workflow state.
Inputs: limit, offset, status, assetId, +2 more. Returns: object
clips_presets_listList Clip PresetsARead-onlyIdempotentInspect
List available clip batch presets and their clipping/caption defaults.
Inputs: no named parameters. Returns: presets
clips_recoverRecover Missing ClipsADestructiveIdempotentInspect
Recover a terminal batch's missing clip count through the persisted recovery workflow. Preserves accepted clips and returns the recovery batch ID. Can spend existing account credits; retry with the identical idempotency key.
Inputs: batchId (required), workspaceId (required), idempotencyKey (required), targetClipCount (required). Returns: object
clips_repairRepair One Clip LayoutBDestructiveIdempotentInspect
Request a layout repair for one managed clip, such as preserving a screen demo or moving captions away from faces. Changes that clip's project; preserves the other clips.
Inputs: clipId (required), idempotencyKey (required), repairMode, workspaceId. Returns: object
clips_reselectRevise Selected MomentADestructiveIdempotentInspect
Replace the source moment for one managed clip using a verified suggestion or explicit time range. Can spend existing account credits. Preserves the other clips; read current state before retrying.
Inputs: clipId (required), selectionMode (required), idempotencyKey (required), lookId, +9 more. Returns: object
clips_status_getRefresh Clip ProgressARead-onlyIdempotentInspect
Read one existing batch's progress, ready clips and renewed signed links without opening or remounting a review widget. Safe for bounded polling and widget refresh; does not recreate or repair clips.
Inputs: batchId (required), workspaceId. Returns: batch
content_performance_listRead Published Content PerformanceARead-onlyIdempotentInspect
Read bounded existing provider-reported engagement in the selected workspace, sorted by views. Filters by format, account and publication window. Returns lifetime counters, saved watch metrics, capture/check times, availability, and saved Project/export lineage when known. includeDetails includes bounded retention and audience tables. Does not import new data, start monitoring or infer attributable leads, sales or revenue.
Inputs: limit (required), range (required), format (required), offset (required), +5 more. Returns: result
customer_link_applySave customer tracking linkAIdempotentInspect
Create a stable HTTPS tracking link or revise its label/enabled state. Destination and content association are immutable. Revisions require expectedRevision; null creates.
Inputs: id (required), label (required), postId (required), enabled (required), +6 more. Returns: link, mutationReceipt
customer_measurements_listRead customer outcomesARead-onlyIdempotentInspect
Read observed link clicks and self-reported outcomes in a bounded window up to 90 days. Counts are not verified conversions. Provider engagement remains separate.
Inputs: to (required), from (required), limit (required), offset (required), +1 more. Returns: links, window, outcomes, linkBounds, +4 more
customer_outcome_applySave self-reported outcomeBIdempotentInspect
Record or revise leads, sales, revenue or another measured outcome with source, time and explicit attribution. Revision history is retained; voided records remain visible. No conversion is inferred from clicks.
Inputs: id (required), kind (required), unit (required), value (required), +10 more. Returns: outcome, mutationReceipt
delete_timeline_itemsDelete Timeline ItemsBDestructiveIdempotentInspect
Preview or delete up to 100 timeline items and optionally remove linked captions.
Inputs: projectId (required), timelineItemIds (required), dryRun, confirmDelete, +3 more. Returns: object
editor_asset_replaceeditor asset replaceADestructiveIdempotentInspect
Replace one shot's media asset while preserving the other timeline items. Revision checked; dryRun previews by default. Requires a current editor snapshot and an asset in the same workspace.
Inputs: dryRun (required), itemId (required), assetId (required), projectId (required), +3 more. Returns: object
editor_assets_inserteditor assets insertBIdempotentInspect
Insert a workspace image, generated shot or audio asset at an explicit project time. Revision checked; dryRun previews by default.
Inputs: dryRun (required), assetId (required), projectId (required), layerIndex (required), +5 more. Returns: object
editor_audio_seteditor audio setADestructiveIdempotentInspect
Adjust one item's volume and audio fades. Revision checked; dryRun previews by default. Preserves the rest of the project.
Inputs: dryRun (required), itemId (required), volume (required), projectId (required), +5 more. Returns: object
editor_composition_editeditor composition editADestructiveIdempotentInspect
Edit composition elements by stable element ID from the editor snapshot: text content, style and animation. Content/style edits preserve placement timing. Optional edit.structure runs ordered insert/move/remove operations before changes. Group by inserting a group and moving children into it. Supply new unique IDs; beforeId null appends. Move coordinates preserveLocal keeps local style and frame offsets, not world position/time. Remove deletes the subtree. Preview reports affected and removed element IDs. Optional edit.duration sets source frames with explicit placements policy: preserve keeps visible windows and syncs unused tails; resizeAll preserves starts/trims and resizes all active placements. Source windows must fit; invalid shortening is rejected. Shared content changes affect all its placements. Omitted fields stay unchanged; null clears a style override; animation values replace the whole property's animation. Attached presets require explicit detachment. Revision checked; dryRun previews by default.
Inputs: edit (required), dryRun (required), itemId (required), projectId (required), +3 more. Returns: object
editor_crop_seteditor crop setADestructiveIdempotentInspect
Adjust the crop of one existing source view after a layout has been applied. Revision checked; dryRun previews by default. Preserves the other shots.
Inputs: crop (required), dryRun (required), itemId (required), projectId (required), +3 more. Returns: object
editor_edit_undoUndo Saved EditADestructiveIdempotentInspect
Restore one saved editor action at the expected current revision. Requires the action ID from edit history and an idempotency key. Existing project data is changed.
Inputs: actionId (required), projectId (required), workspaceId (required), idempotencyKey (required), +1 more. Returns: object
editor_history_listList Edit HistoryARead-onlyIdempotentInspect
Read up to 50 saved edit actions, their labels and undo state. Does not restore or change the project.
Inputs: limit (required), projectId (required), workspaceId (required). Returns: object
editor_items_moveeditor items moveADestructiveIdempotentInspect
Move selected timeline items to explicit times and layers. Revision checked; dryRun previews by default.
Inputs: items (required), dryRun (required), projectId (required), workspaceId (required), +2 more. Returns: object
editor_items_removeeditor items removeBDestructiveIdempotentInspect
Remove selected timeline items and, if requested, their linked captions. Revision checked; dryRun previews by default. The saved action can be undone.
Inputs: dryRun (required), itemIds (required), projectId (required), workspaceId (required), +3 more. Returns: object
editor_snapshot_getRead Editor SnapshotARead-onlyIdempotentInspect
Read the current revision, stable timeline IDs, captions, style and bounded media context before a precise revision. Signed media links are refreshed by reading again.
Inputs: limit (required), offset (required), projectId (required), workspaceId (required), +1 more. Returns: object
editor_text_seteditor text setADestructiveIdempotentInspect
Create or revise one title or text overlay with explicit timing. Revision checked; dryRun previews by default. This edits project text, not spoken audio or captions.
Inputs: spec (required), text (required), dryRun (required), itemId (required), +7 more. Returns: object
exports_caption_track_getRead Export Caption TrackARead-onlyIdempotentInspect
Read a WebVTT caption track from the completed export's immutable canonical speech snapshot, preserving the actual export trims. Returns unavailable for older exports or unverified speech; never fabricates captions from titles or current edited timelines.
Inputs: exportId (required), workspaceId (required). Returns: object
exports_listList ExportsARead-onlyIdempotentInspect
List exports with render status and progress. Completed exports include a signed download URL. Pass exportId to return one export.
Inputs: limit, offset, exportId, projectId, +1 more. Returns: bounds, exports
exports_startStart ExportBDestructiveInspect
Export a BlitzReels video or native carousel and return export and job IDs for status checks.
Inputs: projectId (required), format, resolution, idempotencyKey, +2 more. Returns: export
generation_faceless_createGenerate Faceless VideoADestructiveIdempotentInspect
Turn a script into a full faceless video project: scene plan, generated visuals, optional voiceover, captions, music, and sound. Spends AI credits and returns a job to poll with generation_jobs_get.
Inputs: script (required), voiceId, seriesId, storyKitId, +14 more. Returns: generation
generation_image_createGenerate ImageADestructiveIdempotentInspect
Queue an AI image generation into the BlitzReels media library. Spends AI credits and returns a job to poll with generation_jobs_get.
Inputs: prompt (required), size, model, folderId, +8 more. Returns: generation
generation_jobs_cancelCancel Generation JobADestructiveIdempotentInspect
Request cancellation of the identified queued or running generation. Work already performed can consume credits; cancellation does not establish a refund.
Inputs: jobId (required), workspaceId. Returns: job
generation_jobs_getGet Generation JobARead-onlyIdempotentInspect
Read generation status, failure category, ledger-confirmed credit outcome, prompt history and compatible model alternatives. Alternatives report duration splits, estimated credits and unverified acceptance. reviewUrl opens prompt review and support escalation. Completed jobs include a media ID and download URL.
Inputs: jobId (required), workspaceId. Returns: job
generation_music_createGenerate MusicADestructiveIdempotentInspect
Queue a background music track into the BlitzReels media library. Spends AI credits and returns a job to poll with generation_jobs_get.
Inputs: mood, prompt, workspaceId, idempotencyKey, +1 more. Returns: generation
generation_options_listList Generation OptionsARead-onlyIdempotentInspect
List the models, defaults, limits, and credit costs available for one generation kind before queueing it. Video duration is an enum per model (durations_seconds), not a min-max range.
Inputs: kind (required). Returns: options
generation_plan_briefGet Generation Plan BriefARead-onlyIdempotentInspect
Read a generation brief from rawPrompt. Source-video edits return execution for generation_video_create with required assets and transformation controls. New scenes return an authoring grammar and planJsonSchema for generation_plan_validate. The video creation provenance.originalRequest field retains rawPrompt when supplied. This read does not generate media or spend credits.
Inputs: genre, rawPrompt, aspectRatio, visualStyle, +2 more. Returns: brief
generation_plan_validateValidate Generation PlanARead-onlyIdempotentInspect
Validate a self-authored generation plan against the schema and the target model's real capabilities before execution. Returns directive errors to fix and revalidate; only a valid plan is executable.
Inputs: plan (required). Returns: valid, errors
generation_sound_createGenerate Sound EffectADestructiveIdempotentInspect
Queue a sound effect into the BlitzReels media library. Spends AI credits and returns a job to poll with generation_jobs_get.
Inputs: prompt (required), loop, workspaceId, idempotencyKey, +2 more. Returns: generation
generation_video_createGenerate VideoADestructiveIdempotentInspect
Queue video generation, image animation, source-video editing or character replacement into the media library. Editing accepts referenceVideoAssetIds and transformation controls, including original-audio preservation. Spends AI credits and returns a job readable with generation_jobs_get.
Inputs: prompt (required), seed, model, folderId, +19 more. Returns: generation
generation_voiceover_createGenerate VoiceoverADestructiveIdempotentInspect
Queue a text-to-speech voiceover into the BlitzReels media library. Spends AI credits and returns a job to poll with generation_jobs_get.
Inputs: text (required), speed, voiceId, voiceStyle, +2 more. Returns: generation
hooks_suggestSuggest Clip HooksARead-onlyInspect
Suggest text hooks, existing transcript sentences and visual ranges without editing the project. Defaults to three per layer, count 1-5. Times use project timeline seconds. Included with a daily workspace cap; never starts media analysis. Unsupported options are omitted.
Inputs: count (required), layers (required), projectId (required), workspaceId (required). Returns: text, spoken, visual, language
learning_controlControl learning jobBIdempotentInspect
Cancel a queued or running analysis, recover an unconfirmed dispatch by its existing identity, or deliver a retained result. Resume never repeats an uncertain model call and rejects changed owner direction.
Inputs: jobId (required), action (required), workspaceId (required). Returns: id, error, runId, status, +5 more
learning_getRead learning jobBRead-onlyIdempotentInspect
Read frozen evidence, exact creative lineage, progress and saved lessons for a workspace learning job. Current owner direction overrides saved suggestions.
Inputs: jobId (required), workspaceId (required). Returns: id, error, runId, status, +5 more
learning_quoteInspect learning evidenceBRead-onlyIdempotentInspect
Read bounded Series feedback, metrics, clicks and self-reported outcomes with current owner direction and a cost quote. No model call. Missing or incomparable evidence remains explicit.
Inputs: to (required), from (required), goal (required), language (required), +3 more. Returns: credits, quoteId, evidence, expiresAt, +1 more
learning_startPropose content variationsAIdempotentInspect
Start one bounded model call from a reviewed learning quote and approved credits/USD cap. Saves cited lessons and up to five experimental briefs in the shared brain. Idempotent; never publishes or promises performance.
Inputs: to (required), from (required), goal (required), maxUsd (required), +8 more. Returns: id, error, runId, status, +5 more
media_assets_getGet Media AssetARead-onlyIdempotentInspect
Get metadata and processing state for one media-library asset without returning transcript segments.
Inputs: assetId (required). Returns: asset
media_assets_previewPreview Media AssetARead-onlyIdempotentInspect
Return one bounded JPEG as MCP image content for visual inspection. Images use the stored visual; videos use the existing thumbnail.
Inputs: assetId (required), maxDimension. Returns: asset, preview
media_assets_updateUpdate Media AssetADestructiveIdempotentInspect
Rename one media asset, edit its description, move it to a folder, or change B-roll eligibility. Provide at least one of name, description, folderId, or allowUsingAsBroll.
Inputs: assetId (required), name, folderId, description, +2 more. Returns: txid, asset, updatedFields, mutationReceipt
media_folders_createCreate Media FolderAIdempotentInspect
Create one media-library folder in a workspace and return a retry-safe mutation receipt.
Inputs: name (required), iconType, description, workspaceId, +2 more. Returns: folder, mutationReceipt
media_folders_listList Media FoldersARead-onlyIdempotentInspect
List one bounded level of media-library folders and direct asset counts.
Inputs: limit, offset, workspaceId, parentFolderId. Returns: bounds, folders
media_import_inspectInspect Import URLARead-onlyIdempotentInspect
Inspect a user-provided public social-video or Google Drive URL and return available import metadata without creating media.
Inputs: url (required). Returns: preview
media_import_scan_pageScan Page For VideoARead-onlyIdempotentInspect
Scan a user-controlled public page and return an importable video URL found on it without creating media.
Inputs: url (required), confirmAuthorizedToScan. Returns: resolved
media_import_urlImport Media From URLAInspect
Import video, audio, images, fonts, SVG or JSON from a direct URL into the private workspace library. Returns a durable asset ID and verified contentHashSha256. Fonts, SVG and JSON are limited to 25 MiB.
Inputs: url (required), name, projectId, workspaceId, +5 more. Returns: media
media_listList MediaARead-onlyIdempotentInspect
List media files in user's library (videos, audio, images)
Inputs: limit, offset, assetType, workspaceId. Returns: assets, bounds
media_narration_getRead narration timingARead-onlyIdempotentInspect
Read retained voice inputs, measured duration, audio SHA-256 and word timing. Defaults to 200 words, maximum 500; offset selects the next page. take is null for audio without a retained narration take.
Inputs: limit (required), offset (required), assetId (required), workspaceId. Returns: take, bounds, assetId, wordTimings
media_transcript_getGet Media TranscriptARead-onlyIdempotentInspect
Get transcript summary metadata or a bounded window of transcription segments for a video asset.
Inputs: assetId (required), mode, limit, offset. Returns: error, transcript
media_upload_fileUpload FileAInspect
Import a video, audio, or image file from ChatGPT into the BlitzReels media library. Use this for a file the user attached or picked, and for an image ChatGPT generated in this conversation that the user wants to keep, animate, or edit in BlitzReels.
Inputs: file (required), name, projectId, workspaceId. Returns: media
media_upload_finishFinish Media UploadAInspect
Verify uploaded bytes and save a reusable workspace asset after presigned PUT. Returns contentHashSha256, fileSizeBytes and mimeType.
Inputs: fileName (required), storageKey (required), contentType (required), fileSizeBytes (required), +7 more. Returns: media
media_upload_startStart Media UploadBInspect
Get a presigned URL for direct file upload (for large files)
Inputs: fileName (required), contentType (required), projectId, workspaceId. Returns: uploadInfo
media_upscaleUpscale VideoADestructiveIdempotentInspect
Queue a ByteDance upscale of one stored video asset to 1080p or 4k. Call media_upscale_estimate first. Spends AI credits and returns a new pending media asset to poll with media_assets_get.
Inputs: assetId (required), targetResolution (required), projectId, workspaceId, +1 more. Returns: runId, status, assetId, sourceAssetId, +3 more
media_upscale_estimateEstimate Video UpscaleARead-onlyIdempotentInspect
Estimate ByteDance upscale eligibility and credits for one stored video. Does not spend credits or queue a job. Call this before media_upscale.
Inputs: assetId (required), targetResolution (required), projectId, workspaceId. Returns: eligible, targetFps, sourceLongEdge, targetLongEdge, +4 more
mute_clip_audioMute Clip AudioBDestructiveIdempotentInspect
Set one timeline media item's volume to zero.
Inputs: projectId (required), idempotencyKey (required), timelineItemId (required), expectedRevision. Returns: txid, result, replayed, revision, +8 more
projects_createCreate ProjectBInspect
Create a new private BlitzReels video project.
Inputs: name (required), seriesId, frameRate, aspectRatio, +3 more. Returns: project
projects_duplicateDuplicate ProjectAIdempotentInspect
Duplicate a project with shared source media and copied timeline, captions, settings and framing. Returns clip_id for copied clip projects. Reuse idempotencyKey only with identical inputs.
Inputs: projectId (required), workspaceId (required), idempotencyKey (required), name, +1 more. Returns: id, name, status, clip_id, +7 more
projects_getGet ProjectARead-onlyIdempotentInspect
Get details for one BlitzReels project, including timeline summary, clips, captions, and current recovery state with an app path and next read tool.
Inputs: projectId (required). Returns: error, project
projects_inspectInspect ProjectARead-onlyIdempotentInspect
Read bounded project context for editing, including timeline items, media assets, transcripts, captions, and stable IDs.
Inputs: projectId (required), mode, search, assetLimit, +7 more. Returns: data, mode, bounds
projects_listList ProjectsBRead-onlyIdempotentInspect
List the user's BlitzReels projects with status, duration, and basic metadata.
Inputs: limit, offset, search, status, +1 more. Returns: bounds, projects
publishing_accounts_listRead Connected Publishing AccountsBRead-onlyIdempotentInspect
Read the supported accounts available through the existing workspace and provider access rules. Does not connect new accounts, publish, schedule or bypass provider review.
Inputs: limit (required), offset (required), workspaceId (required). Returns: result
publishing_connections_listList Publishing ConnectionsARead-onlyIdempotentInspect
List Instagram accounts connected through the BlitzReels UI for the authenticated workspace, including their connection status.
Inputs: no named parameters. Returns: count, connections
publishing_instagram_scheduleSchedule Instagram PublishADestructiveInspect
Schedule a completed project export to Instagram. Optional includeAffiliateCta appends Try BlitzReels for free plus the Affonso tracking URL. Requires an active Instagram account connected in the BlitzReels UI.
Inputs: projectId (required), scheduledFor (required), caption, exportId, +8 more. Returns: postId, status, exportId, platform, +5 more
publishing_post_getVerify Video PublicationARead-onlyIdempotentInspect
Read the current targets for one publishing receipt with scheduled/published state and verified remote URLs. Does not retry or publish a failed target.
Inputs: postId (required), workspaceId (required). Returns: result
publishing_video_scheduleSchedule Reviewed Video PublicationADestructiveIdempotentInspect
Schedule a selected existing video asset to explicit active YouTube, Instagram, Facebook, TikTok, LinkedIn or Threads accounts connected in the BlitzReels UI, using reviewed copy, privacy/consent choices, synthetic-media disclosure, time and timezone. Requires confirmPublish=true. Existing workspace permissions and provider access rules apply. A scheduled receipt is not proof of publication.
Inputs: targets (required), workspaceId (required), scheduled_for (required), confirmPublish (required), +8 more. Returns: result
recording_sets_clips_createClip a Synchronized RecordingADestructiveIdempotentInspect
Produce a batch from a ready synchronized camera and screen recording, with optional clip count, maximum duration and caption look. Preserves readable screen context through the existing layout pipeline. Can spend existing credits; follows clips_get with the returned batch_id.
Inputs: clipCount (required), workspaceId (required), captionThemeId (required), idempotencyKey (required), +2 more. Returns: result
recording_sets_createCreate Synchronized RecordingAIdempotentInspect
Create an empty camera and screen recording set in the explicit workspace. Requires existing recording-set access; does not import files or start processing.
Inputs: name (required), workspaceId (required), idempotencyKey (required). Returns: result
recording_sets_finalizeSynchronize Recording TracksBDestructiveIdempotentInspect
Finalize the collected camera and screen tracks and queue analysis. Can spend existing transcription credits. Inspect returned alignment and warnings before clipping.
Inputs: workspaceId (required), idempotencyKey (required), recordingSetId (required). Returns: result
recording_sets_getInspect Synchronized RecordingARead-onlyIdempotentInspect
Read one camera and screen recording set, its primary speaker, content windows, alignment and warnings. Separate audio-only tracks are not supported.
Inputs: workspaceId (required), recordingSetId (required). Returns: result
recording_sets_listList Synchronized RecordingsBRead-onlyIdempotentInspect
Read bounded camera and screen recording sets in the selected workspace with status, duration and alignment warnings.
Inputs: limit (required), offset (required), status (required), workspaceId (required). Returns: result
recording_sets_track_attachAttach Camera or Screen RecordingAIdempotentInspect
Attach one existing authorized video asset as a camera or screen track. Specify the main speaker when known; alignment happens during finalization.
Inputs: role (required), asset_id (required), is_primary (required), workspaceId (required), +4 more. Returns: result
series_applyApply SeriesBDestructiveIdempotentInspect
Create or replace a Growth+ Series identity and defaults. defaultCreationMode selects podcast branding or faceless Story Kit defaults; membership stays mixed. Updates require expectedRevision. Existing content keeps its settings.
Inputs: name (required), seriesId (required), storyKitId (required), description (required), +7 more. Returns: series, mutationReceipt
series_assignAssign Series ContentBDestructiveIdempotentInspect
Assign, move or detach one source or project using expectedSeriesId. Moving a source does not move existing clips or change branding.
Inputs: kind (required), seriesId (required), contentId (required), workspaceId (required), +2 more. Returns: id, kind, changed, seriesId, +2 more
series_contentList Series ContentARead-onlyIdempotentInspect
List sources or projects in a Series. Null seriesId lists standalone content. sourceId filters projects by clip origin.
Inputs: kind (required), limit (required), offset (required), search (required), +3 more. Returns: items, bounds
series_deleteDelete SeriesADestructiveIdempotentInspect
Delete the Series container at an expected revision and detach its content. Sources, projects and exports are preserved.
Inputs: seriesId (required), workspaceId (required), idempotencyKey (required), expectedRevision (required). Returns: id, detachedSources, mutationReceipt, contentPreserved, +1 more
series_getGet SeriesCRead-onlyIdempotentInspect
Read a Series identity, creative defaults and revision.
Inputs: seriesId (required), workspaceId (required). Returns: series
series_listList SeriesCRead-onlyIdempotentInspect
List optional Series with bounded counts and cover previews.
Inputs: limit (required), offset (required), workspaceId (required). Returns: items, bounds
story_kits_applyApply Story KitCDestructiveIdempotentInspect
Create or update a Story Kit with optimistic concurrency and an idempotent mutation receipt.
Inputs: name (required), visualStyle (required), idempotencyKey (required), facts, +8 more. Returns: storyKit, mutationReceipt
story_kits_getGet Story KitBRead-onlyIdempotentInspect
Inspect one Story Kit and its revision before generating or updating a story.
Inputs: storyKitId (required), workspaceId. Returns: storyKit
story_kits_listList Story KitsBRead-onlyIdempotentInspect
List bounded reusable Story Kits that bind characters, locations, style, facts, and narrator voice.
Inputs: limit, offset, workspaceId. Returns: bounds, storyKits
timeline_audio_addAdd Audio To TimelineBInspect
Place an audio asset onto a BlitzReels project timeline at a timestamp for voiceover, music, or sound.
Inputs: assetId (required), projectId (required), loop, volume, +4 more. Returns: result
timeline_media_addAdd Media To TimelineBInspect
Place an image or video asset onto a BlitzReels project timeline at a timestamp, including B-roll and static images.
Inputs: assetId (required), projectId (required), layerIndex, startSeconds, +5 more. Returns: result
timeline_split_applyApply Timeline SplitBDestructiveIdempotentInspect
Split one timeline item at the expected project revision. Changes existing timeline state and returns a retry-safe receipt.
Inputs: projectId (required), snapToFrame (required), idempotencyKey (required), splitAtSeconds (required), +2 more. Returns: object
timeline_split_previewPreview Timeline SplitBRead-onlyIdempotentInspect
Preview splitting one timeline item without changing the project.
Inputs: projectId (required), snapToFrame (required), splitAtSeconds (required), timelineItemId (required), +1 more. Returns: object
timeline_trim_applyApply Timeline TrimBDestructiveIdempotentInspect
Trim or extend one timeline item at the expected project revision. Changes existing timeline state and returns a retry-safe receipt.
Inputs: projectId (required), snapToFrame (required), idempotencyKey (required), timelineItemId (required), +3 more. Returns: object
timeline_trim_previewPreview Timeline TrimBRead-onlyIdempotentInspect
Preview trimming or extending one timeline item without changing the project.
Inputs: projectId (required), snapToFrame (required), timelineItemId (required), expectedRevision (required), +2 more. Returns: object
update_timeline_clipUpdate Timeline ClipBDestructiveIdempotentInspect
Update one timeline item's start, duration, trim, layer, ignored state, or blurred background. Provide at least one field to update besides timelineItemId.
Inputs: projectId (required), idempotencyKey (required), timelineItemId (required), ignored, +7 more. Returns: txid, result, replayed, revision, +8 more
video_assets_approveApprove Previews and Produce VideoADestructiveIdempotentInspect
After the user approves the generated previews and animation cost, confirmApproved=true starts scene animation, narration and editable timeline assembly. Can replace the project's generated timeline and spend existing credits. Follow the revision and then export the finished project.
Inputs: projectId (required), revisionId (required), workspaceId (required), idempotencyKey (required), +1 more. Returns: result
video_feedback_saveSave Video Quality FeedbackADestructiveIdempotentInspect
Save the user's 1-5 rating and optional quality category/comment against one completed playable video export. Replaces that user's previous feedback for this export; does not change accepted clips or defaults. Requires the feedback storage migration to be installed.
Inputs: rating (required), comment (required), category (required), exportId (required), +2 more. Returns: object
video_storyboard_approveApprove Storyboard PreviewsADestructiveIdempotentInspect
After showing the storyboard and its credit estimate, confirmApproved=true starts production of reference images and scene keyframes. Spends existing credits. This stage produces reviewable previews, not animated videos.
Inputs: projectId (required), revisionId (required), workspaceId (required), idempotencyKey (required), +1 more. Returns: result
video_storyboard_asset_regenerateRegenerate Selected Storyboard PreviewADestructiveIdempotentInspect
Replace the identified preview after user approval of the new credit cost. A scene_keyframe changes one keyframe; a character_anchor refreshes its dependent keyframes; a style_anchor refreshes every keyframe. Preserves unaffected previews. Does not regenerate an already finished video shot.
Inputs: projectId (required), asset_type (required), revisionId (required), workspaceId (required), +4 more. Returns: result
video_storyboard_createPlan an Approved Video ScriptADestructiveIdempotentInspect
Create a vertical video storyboard for the user-approved script in an existing project. Spends planning credits; returns scene narration, factual review notes, references and the production credit estimate. Does not generate images or animate video. Existing account access applies.
Inputs: script (required), projectId (required), workspaceId (required), idempotencyKey (required), +20 more. Returns: result
video_storyboard_getReview Video StoryboardARead-onlyIdempotentInspect
Read one authorized storyboard revision, its scene and reference previews, estimate, approvals and bounded polling guidance. Refreshes signed previews. Complete means the editable timeline is assembled; use exports_start and exports_list for a downloadable MP4.
Inputs: projectId (required), revisionId (required), workspaceId (required). Returns: result
video_storyboard_reviseRevise Selected Storyboard ScenesAIdempotentInspect
Create a new immutable draft from a known revision with selected scene, character or model changes. Preserves other scene definitions; requires review and production approval again. Does not generate media or overwrite an approved revision.
Inputs: projectId (required), revisionId (required), workspaceId (required), idempotencyKey (required), +5 more. Returns: result
visuals_applyApply visual presetsADestructiveIdempotentInspect
Create or update up to 20 visual blocks in one call after edit timing is settled. Presets: broll-headline, steps, quote, end-screen, key-number, before-after, screenshot-focus, chapter. IDs are scoped to the project; repeating an ID updates it. Asset IDs must belong to the workspace. Atomic, undoable; dryRun validates without writing. Returns IDs and revision. No generation pass.
Inputs: items (required), dryRun (required), projectId (required), idempotencyKey (required), +1 more. Returns: items, dryRun, success, replayed, +3 more
workspace_brand_scanInspect Supplied Business WebsiteBDestructiveIdempotentInspect
Start extracting a brand profile from the exact website the user supplied and authorized to scan. Saves a draft profile for review; does not apply discovered fields to existing videos. Can spend existing account credits.
Inputs: websiteUrl (required), workspaceId (required), idempotencyKey (required), confirmAuthorizedToScan (required). Returns: object
workspace_brand_scan_getRead Website Brand DraftBRead-onlyIdempotentInspect
Read one authorized website extraction run and its draft business profile. Show the extracted fields to the user for review before saving them as defaults.
Inputs: runId (required), workspaceId (required). Returns: object
workspace_context_getRead Business ContextBRead-onlyIdempotentInspect
Read the selected workspace's business audience, offer, reviewed brand defaults, protected vocabulary, editorial purpose, language, avoided terms, pronunciation notes and existing account entitlements. Returns current export quality, watermark constraints, public plan names, monthly USD prices, included AI credits and the pricing upgrade URL.
Inputs: workspaceId (required). Returns: object
workspace_context_saveSave Reviewed Business ContextADestructiveIdempotentInspect
Save the user-reviewed business name, audience, offer, conversion goal, tone, protected vocabulary and editorial preferences for the selected workspace. Requires workspace settings permission and confirmReviewed=true; changes future assistant guidance, preserving existing projects. Pronunciation notes guide script drafting; they do not retime or replace source speech.
Inputs: tone (required), offer (required), audience (required), brandName (required), +6 more. Returns: object
workspaces_listList WorkspacesBRead-onlyIdempotentInspect
List bounded workspaces the connected user belongs to, with their role and default workspace. Selecting a workspace for the task does not change account defaults.
Inputs: limit (required), offset (required). Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Turn long videos into captioned, reframed short clips, thumbnails, and social posts.
Turn a long video into short vertical clips: find moments, add captions, reframe, export.
Turn long videos into AI-curated short clips: caption, reframe, thumbnail, schedule, and publish.
Turn long videos into viral vertical shorts and publish them to TikTok, Instagram and YouTube.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceTurns long-form videos into short-form clips (TikTok/Reels) by reasoning over word-timestamped transcripts, with silence-aware rendering, STT-based validation, and optional reframing/captions.-
- AlicenseNot gradedqualityBmaintenanceEnables local-first video editing for creators and AI agents through tools for auto-editing, shorts, captions, music, QC, transcription, reframing, rendering, and project handoff while footage stays on the user's machine.106 npm3MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to clip videos and live streams into scored, captioned shorts, then plan, preview, schedule, and manage posts across eight social platforms with tools for channels, analytics, trending discovery, and usage.451 npmMIT
- AlicenseAqualityBmaintenanceOpenShorts turns long videos into vertical clips readys for Social Media posting88,534MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.