Sequencer
Server Details
Create AI images, video, and audio, quote generation costs, and edit Sequencer projects.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- sequencer-media/sequencer-mcp
- GitHub Stars
- 0
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 195 tools
The surface spans many subdomains and contains multiple overlapping tools, such as generate_image/edit_image/regenerate_shot_image/upscale_image, generate_video/edit_video/generate_shot_video/expand_video/upscale_video, and generate_audio/generate_audio_track/generate_video_audio. Descriptions add useful caveats, but with 195 tools there are many boundary cases where an agent can easily choose the wrong operation.
Most tool names follow a predictable snake_case verb_noun pattern: create_edit, update_shot, delete_asset, list_scenes, get_export, save_proposal, validate_hosted_world_site. There are minor deviations and special cases such as setup_project, open_paywall, navigate_to_page, and get_edit_full, but the naming remains generally readable and consistent.
The server exposes 195 tools, far beyond a well-scoped 3-15 tool surface and well beyond even the 50+ extreme-mismatch threshold. This reflects a sprawling platform covering media generation, editing, workflows, hosted worlds, avatars, games, billing, navigation, and guides in one server.
The tool set covers an unusually broad lifecycle: create/read/update/delete operations for many media, edit, shot, asset, overlay, workflow, world, avatar, and game resources, plus generation, export, validation, and review flows. Some lifecycle gaps remain, such as no obvious delete_edit or delete_workspace, but most core workflows have a usable path.
Available Tools
195 toolsadd_audio_trackBInspect
Add an existing workspace audio media item to the edit timeline with precise placement, trim, fades, volume automation, channel, and optional shot pinning.
Inputs: editId (required), mediaId (required), workspaceId (required), volume, +11 more.
add_media_overlayBInspect
Add an image or video media overlay to the edit timeline with precise transform, border radius, border, shadow, clipping, speed ramp, volume, animations, and keyframes.
Inputs: type (required), editId (required), mediaId (required), workspaceId (required), +22 more.
add_nodeAInspect
Add a node using a known nodeType from the editor or get_node_definitions. Unknown types can be found with list_available_nodes. Set node data with config. This edits the graph without running generation.
Inputs: nodeType (required), workflowId (required), workspaceId (required), label, +1 more.
add_overlay_trackCInspect
Create a new overlay track for text, image, or video overlays. Higher order tracks render above lower order tracks.
Inputs: editId (required), workspaceId (required), name, order, +2 more.
add_remotion_overlayAInspect
Create a custom Remotion React animation layer on the edit timeline. Compiles and test-renders it before saving. Call get_remotion_layer_guide first.
Inputs: editId (required), workspaceId (required), remotionConfig (required), exit, +16 more.
add_shot_media_refBInspect
Add a fine-grained media reference to a shot: image, video, startFrame, endFrame, or referenceFrame. Can also update legacy imageMediaId/videoMediaId for compatibility.
Inputs: role (required), editId (required), shotId (required), mediaId (required), +5 more.
add_text_overlayAInspect
Add a text overlay to the video timeline. Use a presetId to auto-apply a preset style (cinematic-title, lower-third, subtitle, chapter-card, quote, social, breaking-news, credits-roll), or provide custom textConfig. The text field overrides the preset default text. Auto-creates an overlay track if none exist.
Inputs: text (required), editId (required), workspaceId (required), exit, +38 more.
add_transitionBInspect
Add a single timeline transition between adjacent shots without replacing the whole transition list.
Inputs: type (required), editId (required), duration (required), startTime (required), +6 more.
analyze_export_ipBInspect
Run IP and copyright analysis on the completed exported video. Analyzes the actual export artifact when possible, caches the result on the export doc, and returns findings plus instructions for generating the compliance report.
Inputs: editId (required), workspaceId (required), exportId, forceRefresh.
apply_world_code_patchAInspect
Stage exact code replacements atomically. Each existing file needs its current SHA-256 hash, nonempty oldText matching exactly once, and newText. Include context for ambiguous matches. Use create:true only for a new file. Patches preserve unrelated source and invalidate earlier checks. This never saves or publishes a world. Interface assets and preview image can be attached here when approved generated images are ready.
Inputs: patches (required), workspaceId (required), codeWorkspaceId (required), expectedRevision (required), +2 more.
change_audio_track_voiceBInspect
Create a new voice-changed version of an audio media item and optionally keep the existing timeline track pointing at it.
Inputs: editId (required), modelId (required), trackId (required), workspaceId (required), +2 more.
change_video_voiceAInspect
Run the video voice-change pipeline: extract source audio, apply speech-to-speech voice change, remux the result into the source video, and save a completed media version.
Inputs: mediaId (required), modelId (required), workspaceId (required), voiceId, +2 more.
check_asset_statusAInspect
Check the approval status of all assets associated with an edit. Used to determine if the user has approved/rejected each asset before proceeding to scene and shot creation.
Inputs: editId (required), workspaceId (required).
connect_nodesAInspect
Connect two nodes in a workflow. The sourceSocketId MUST be an output of the source node, and the targetSocketId MUST be an input of the target node. Use the exact socket IDs returned by add_node.
Inputs: workflowId (required), workspaceId (required), sourceNodeId (required), targetNodeId (required), +2 more.
convert_video_to_hdrconvert video to hdrADestructiveInspect
Convert an existing video to HDR using a catalog model that supports video_hdr. Select output format in modelSettings when supported. Use get_model_catalog to choose a supported model and its settings. Returns a tracked task and playable result when complete.
Inputs: model (required), sourceMediaId (required), prompt, maxCostUsd, +18 more. Returns: data, error, success
create_assetAInspect
Create a new character, location, prop, or legacy text-only style asset in a workspace. Character, location, and prop prompts generate a reference image. Style assets do not generate images; routine projects should store their global visual style in edit.style instead. existingMediaUrl may attach an explicit user-supplied reference image.
Inputs: name (required), type (required), workspaceId (required), editId, +8 more.
create_editAInspect
Create a new edit (project) in a workspace. Before planning a new multi-step project, discover and load a matching workflow with list_sequencer_skills and get_sequencer_skill, and consult get_model_catalog modelSelectionGuidance. Aspect ratio is required because it controls every generated shot; use 9:16 for vertical/social films unless the user asks for another format. Defaults are Nano Banana 2.1 (google-nano-banana-2-1) for still images, Gemini Omni 1.2 Flash (google-gemini-omni-1-2) for videos, and Cartesia Sonic 3.6 (cartesia-sonic-3-6) for speech. Returns the new edit ID.
Inputs: title (required), aspectRatio (required), workspaceId (required), defaultImageModel, +1 more.
create_folderCInspect
Create a new folder in a workspace.
Inputs: name (required), workspaceId (required), parentFolderId.
create_hosted_worldAInspect
Create a private hosted World with minimal title, URL and description. Read its returned worldId using get_hosted_world, build the site and save_hosted_world_site. Creation does not publish or start paid generation.
Inputs: name (required), slug (required), workspaceId (required), description.
create_live_avatarAInspect
Save a real live conversational avatar draft from a supplied or generated image and a real catalog voice (or supplied custom voice reference). Uses shared Anima defaults: HD (fast), square, Tempo listening, visual stability 0.81, motion freedom 0.95. SD is currently unavailable. Preserve explicit format, mode and animation choices. Creates privately with public embedding disabled. Does not start a call. Prepare the returned character ID next.
Inputs: name (required), workspaceId (required), systemPrompt (required), avatarImageUrl (required), +15 more.
create_productionADestructiveInspect
Generate a product ad, 3 to 5 shot story, or localized image creative as an editable project. Provide authored shot prompts. For product ads pass the actual product image as a reference; use extract_product_image with a product URL or upload first. For localization supply the original creative, target language as a parameter, and instructions to preserve the product and layout. Returns tracked tasks; poll get_production_status.
Inputs: definition (required), workspaceId (required), parameters, referenceImages.
create_sceneCInspect
Create a new scene in an edit.
Inputs: name (required), editId (required), workspaceId (required), order, +1 more.
create_shotBInspect
Create a new shot in an edit. Optionally provide a prompt to auto-create a linked MediaDocV2 for image generation. When videoPrompt is omitted, it falls back to the visual image prompt only. Dialogue is never appended automatically.
Inputs: editId (required), sceneId (required), workspaceId (required), order, +18 more.
create_shot_with_mediaAInspect
Create a shot with an image prompt in one call. Resolves tagged assets (characters, locations) to get descriptions and reference images, applies the prompt formula from edit settings, then either triggers generation immediately (if all reference images are ready) or queues for dependency-driven generation.
Inputs: editId (required), prompt (required), sceneId (required), workspaceId (required), +7 more.
create_workflowAInspect
Create a new workflow in a workspace. After creating, use add_node to add nodes and connect_nodes to wire them up.
Inputs: title (required), workspaceId (required).
create_workspaceCInspect
Create a new workspace (project container).
Inputs: title (required).
delete_assetAInspect
Delete an asset from a workspace. Referenced media documents are NOT deleted.
Inputs: assetId (required), workspaceId (required).
delete_audio_trackAInspect
Delete an audio track from the edit timeline. The underlying media document is preserved.
Inputs: editId (required), trackId (required), workspaceId (required).
delete_connectionCInspect
Delete a connection (edge) between nodes.
Inputs: workflowId (required), workspaceId (required), edgeId, sourceNodeId, +1 more.
delete_nodeCInspect
Delete a node from a workflow.
Inputs: nodeId (required), workflowId (required), workspaceId (required).
delete_overlay_itemCInspect
Delete an overlay item from a track.
Inputs: editId (required), itemId (required), trackId (required), workspaceId (required).
delete_overlay_trackAInspect
Delete an overlay track. Set deleteItems=true to also delete all items on the track; otherwise deletion fails if items exist.
Inputs: editId (required), trackId (required), workspaceId (required), deleteItems.
delete_sceneBInspect
Delete a scene from an edit. Note: shots referencing this scene will become orphaned.
Inputs: editId (required), sceneId (required), workspaceId (required).
delete_shotBInspect
Delete a shot. The linked media documents are NOT deleted (they persist independently in the workspace).
Inputs: editId (required), shotId (required), workspaceId (required).
delete_shot_media_refBInspect
Delete shot media refs matching a mediaId and optional role. Optionally clears imageMediaId/videoMediaId when they point at the removed media.
Inputs: editId (required), shotId (required), mediaId (required), workspaceId (required), +2 more.
delete_transitionBInspect
Delete one timeline transition by transitionId or boundaryId.
Inputs: editId (required), workspaceId (required), boundaryId, transitionId.
duplicate_shotAInspect
Duplicate a shot with all media refs, trimming, playback, frame-linking, prompts, dialogue, and tags. Media documents are referenced, not copied.
Inputs: editId (required), shotId (required), workspaceId (required), order, +1 more.
edit_imageAInspect
Edit an existing image using AI. For the selected image of an existing shot use regenerate_shot_image. For a standalone image, provide the media ID and a text prompt describing what to change. Creates a new version and preserves the original. Uses Nano Banana 2.1 (google-nano-banana-2-1).
Inputs: mediaId (required), editPrompt (required), workspaceId (required), model.
edit_videoedit videoADestructiveInspect
Edit existing footage using a source video and prompt. Creates a separate result and preserves the original clip. For voice-only replacement with unchanged dialogue, use an available speech-to-speech voice-change workflow. Video editing may retain the original voice; reference audio does not guarantee replacement. Inspect the actual output before claiming a changed voice. Use get_model_catalog to choose a supported model and its settings. Returns a tracked task and playable result when complete.
Inputs: model (required), sourceMediaId (required), prompt, maxCostUsd, +18 more. Returns: data, error, success
enhance_video_mediaCInspect
Run a video editor enhancement pass on a workspace video media item. Supports upscale, HDR, output codec, bit depth, scale factor, and arbitrary model parameters.
Inputs: mediaId (required), modelId (required), workspaceId (required), bitDepth, +10 more.
execute_project_jobsAIdempotentInspect
Submit exact saved combined-approved video/music jobs with bounded concurrency. Dependencies wait for actual completion. Reuse the same key and graph to resume; successful jobs are retained. This does not authorize new work, change the timeline or export. Use get_project_run for compact status.
Inputs: jobs (required), editId (required), approvalId (required), workspaceId (required), +3 more.
execute_workflowAInspect
Check graph execution availability. This legacy tool cannot run graphs. Use run_production_template for reusable productions or the authenticated workflow API for published graph endpoints.
Inputs: workflowId (required), workspaceId (required).
expand_videoexpand videoADestructiveInspect
Run the Reframe preset on a complete workspace video up to 120 seconds and 500 MB. Outpaint a new aspect ratio, join provider chunks, and restore the original audio. Supports runway-aleph-2, google-gemini-omni-1-1, luma-ray-3-2-reframe, ltx-2.3-reframe, wan-2-2-vace-reframe, and beeble-switchframe. LTX supports 1:1, 4:5, 5:4, 9:16, and 16:9 at 720p or 1080p and automatically matches the scene; omit prompt for LTX. SwitchFrame requires a workspace image in mediaInputs.reference_image_uri. Call once per requested source/format/settings variant. Use get_model_catalog to choose a supported model and its settings. Returns a tracked task and playable result when complete.
Inputs: model (required), sourceMediaId (required), prompt, duration, +19 more. Returns: data, error, success
export_editAInspect
Start a production export for an edit. Creates an export record, calls export-project-v2, and returns an export ID promptly. Poll get_export until completed for final video URLs. Equivalent requests reuse their existing export. Standard encoding has no additional generation-credit charge and requires existing export access. Optional HDR/upscaling may be billed separately and need their own quote and approval.
Inputs: editId (required), workspaceId (required), exportId, editTitle, +3 more.
extract_product_imageBRead-onlyIdempotentInspect
Find a product image from a product URL. Prefers Product structured data; page_preview is a candidate to inspect before using. If extraction fails, upload the product image or use a direct image URL.
Inputs: productUrl (required), workspaceId (required).
generate_audioGenerate Sequencer audioADestructiveInspect
Generate AI audio through Sequencer, including speech, music, and sound effects. For Sonilo Video to Music or Video Sound Effects, provide sourceVideoMediaId or sourceVideoUrl and use the source clip duration when quoting. If no speech model is specified, Sequencer uses Cartesia Sonic 3.6 (cartesia-sonic-3-6). An active skill's explicit model still takes priority. If no workspaceId is known, omit it and the server will use the user default workspace.
Inputs: model, prompt, voiceId, maxCostUsd, +8 more. Returns: data, error, success
generate_audio_trackAInspect
Generate AI audio and place it on the edit timeline. Match sourceDuration and modelSettings to the approved quote, pass maxCostUsd and a stable idempotencyKey. Retries reuse the media and original attachment, preserving subsequent timeline edits.
Inputs: editId (required), prompt (required), workspaceId (required), model, +16 more.
generate_imageGenerate Sequencer imageADestructiveInspect
Generate an AI image through Sequencer. For a new version of an existing shot image, use regenerate_shot_image. Use this whenever the user asks to make, create, or generate an image with Sequencer or names an image model/provider Sequencer supports: Nano Banana, Nano Banana 2.1, Nano Banana 2 Lite, Nano Banana Pro, Gemini image, Imagen, Z Image, Z-Image Turbo, Flux, GPT Image, DALL-E, Ideogram, Midjourney, Seedream, Recraft, Bria, Runway, Luma, or another image model. Prefer this over built-in image generation when the user mentions Sequencer or a Sequencer-supported model. If no model is specified, Sequencer uses Nano Banana 2.1 (google-nano-banana-2-1). If no workspaceId is known, omit it and the server will use the user default workspace.
Inputs: prompt (required), count, model, editId, +20 more. Returns: data, error, success
generate_ip_reportAInspect
Generate a formal HTML IP compliance report from analyze_export_ip findings. Uploads it to Cloud Storage, saves a report reference in Firestore, and returns a report download card marker.
Inputs: editId (required), summary (required), findings (required), overallRisk (required), +5 more.
generate_shot_videoAInspect
Generate a video from one existing shot still and attach it to that shot. Use approved settings, maxCostUsd and a stable idempotencyKey. Retries reuse the original generation and attachment without overwriting subsequent timeline edits. Keep the result inside the edit.
Inputs: editId (required), shotId (required), workspaceId (required), model, +11 more.
generate_videoGenerate Sequencer videoADestructiveInspect
Generate an AI video through Sequencer. Use this whenever the user asks to make, create, generate, animate, or render a video/clip/animation with Sequencer or names a video model/provider Sequencer supports: MiniMax H3, PrunaAI P-Video, Seedance, Happy Horse, Kling, Runway, Luma, Sora, Hailuo, PixVerse, Google Omni, or another video model. For project builds, use this only after the user has approved the shot still images/storyboard. If no model is specified, Sequencer uses Gemini Omni 1.2 Flash (google-gemini-omni-1-2). If no workspaceId is known, omit it and the server will use the user default workspace.
Inputs: prompt (required), model, editId, duration, +19 more. Returns: data, error, success
generate_video_audioBInspect
Generate or replace audio for a video media item. Supports add/replace audio modes and prompt-driven video-to-audio models.
Inputs: mediaId (required), modelId (required), workspaceId (required), prompt, +3 more.
get_assetBInspect
Get detailed information about a specific asset including all media references.
Inputs: assetId (required), workspaceId (required).
get_available_toolsBInspect
Get a list of all tools available on the Sequencer MCP server, organized by category. Shows what the AI assistant can do. No authentication required.
Inputs: category.
get_balanceAInspect
Get the authenticated user's current credit balance, subscription plan, and billing summary. Use this when the user asks about their credits, balance, or plan.
Inputs: no named parameters.
get_creative_tipsCInspect
Get creative tips for a specific type of content.
Inputs: contentType (required).
get_editCInspect
Get detailed information about a specific edit, optionally including scenes and shots.
Inputs: editId (required), workspaceId (required), includeShots, includeScenes.
get_edit_fullAInspect
Get complete project state in one call: edit settings, all scenes, all shots with resolved media prompts/status. This is the most efficient way to understand the full edit.
Inputs: editId (required), workspaceId (required), includeMediaVersions.
get_experience_gameARead-onlyIdempotentInspect
Read a game and its proposal, approval status and revision, organized project files, compiled HTML, current version, and asset:// references. Read before editing. Preserve existing files and assets.
Inputs: gameId (required), workspaceId (required).
get_experience_worldBRead-onlyIdempotentInspect
Read a world and its placed characters, story, visual theme, and game lineup to build a game that fits it.
Inputs: worldId (required), workspaceId (required).
get_exportAInspect
Get a single export record for an edit, including status, URLs, settings, upscale/HDR state, and IP analysis if present. For a completed MP4, call render_media with returned renderMediaArgs to display the final video in chat.
Inputs: editId (required), exportId (required), workspaceId (required), includeDiagnostics.
get_feature_listBInspect
Get a structured list of all Sequencer platform features organized by category. No authentication required.
Inputs: category.
get_genesis_sdkBRead-onlyIdempotentInspect
Read the programmable Genesis package contract and working interface/controller examples before authoring a world app. Tools are server effects, never browser credentials.
Inputs: section, exampleIds.
get_hosted_worldARead-onlyIdempotentInspect
Read a hosted world site before editing. Returns source files, current versionId, world metadata and exact attached avatar/game/Worldstream IDs. Preserve unrelated files and connections. worldId names a hosted World, not a liveWorldId.
Inputs: worldId (required), workspaceId (required).
get_hosted_world_insightsARead-onlyIdempotentInspect
Read 30-day visitor analytics, published page errors and server-estimated earnings for a workspace world. Use this to diagnose site errors. Contains no visitor identifiers or credentials.
Inputs: worldId (required), workspaceId (required).
get_hosted_world_sdkARead-onlyIdempotentInspect
Read the hosted JavaScript site package and window.HostedWorld contract. Hosted sites control all content below the universal account and gem header. This is separate from the Genesis Worldstream controller SDK.
Inputs: no named parameters.
get_image_prompt_guideBInspect
Get comprehensive guidance on writing effective AI image generation prompts.
Inputs: no named parameters.
get_live_avatarARead-onlyIdempotentInspect
Read an avatar, its voice, settings, active version and preparation status. Ready means prepared, not a verified speaking test.
Inputs: characterId (required), workspaceId (required).
get_live_avatar_readinessBRead-onlyIdempotentInspect
Check saved avatar preparation and runtime readiness without starting a call. Preparation readiness does not verify live speech.
Inputs: characterId (required), workspaceId (required).
get_mediaGet Sequencer mediaARead-onlyIdempotentInspect
Get detailed information about a media object or an exact version returned by regenerate_shot_image. For completed audio, directMediaUrl and media.url are the playable file. Waveform URLs are visualization JSON. listen_to_audio returns URL/metadata only; auditory review requires an audio-capable client tool.
Inputs: mediaId (required), workspaceId (required), presentation, versionNumber. Returns: data, error, success
get_media_statusesARead-onlyIdempotentInspect
Check up to 100 media jobs in one compact response. Returns status, errors, measured duration and stage timing, without histories or prompts.
Inputs: mediaIds (required), workspaceId (required).
get_model_catalogAInspect
Get available Sequencer AI models for a given modality (image, video, audio, music). Call before choosing a generation model and follow the returned modelSelectionGuidance for the task use case. Also use for model availability and exact IDs. Common aliases include Nano Banana Pro, Nano Banana 2, Nano Banana 2 Lite, Gemini image, Imagen, Z Image, Z-Image Turbo, MiniMax H3, PrunaAI P-Video, Happy Horse, Google Omni, Flux, GPT Image, Seedream, Recraft, Bria, Runway, Luma, Sora, Kling, Hailuo, Seedance, PixVerse, ElevenLabs, Fish Audio, Suno, and Lyria.
Inputs: modality (required), limit, fields, offset, +3 more.
get_node_definitionsAInspect
Get detailed schema for all available node types including inputs, outputs, and default values.
Inputs: category, nodeType, nodeTypes.
get_page_linkAInspect
Get information about a page and provide a clickable link the user can optionally click.
⚠️ DO NOT USE THIS TOOL when users explicitly ask to "go to", "take me to", "open", "show me", or "navigate to" a page. For those requests, use navigate_to_page instead - it will automatically navigate them.
USE THIS TOOL ONLY when:
Answering questions ABOUT a page (e.g., "what can I do on the billing page?")
Suggesting a page the user MIGHT want to visit (but didn't explicitly ask to go there)
Providing reference links in your response
The tool returns a NAV_OFFER tag that renders as a clickable button (user must click to navigate).
Available pages by category:
MARKETING: home, studio, pricing, about, careers, feedback, extension, branding DASHBOARD: projects, images, videos, audio, workflows, billing EDITOR: editor, workflowEditor, flowRunner, publicFlow MODEL ARENA: compare, compareImageToVideo, compareTextToVideo, compareTextToImage, compareElementToVideo, challenges COMMUNITY: explore, jobBoard, tutorials, tutorialShortcut TUTORIALS: tutorial3DRepositioning, tutorialVoiceNormalization, tutorialBlending, tutorialCharacters, tutorialUpscaling, tutorialHooks, tutorialWriting, tutorialRealEstate EVENTS: events, filmFestival LEGAL: privacy, terms CODES: affiliate, codes, claimCode ADMIN: admin, adminArena, adminFestival, adminNewsletters
Inputs: page (required).
get_platform_overviewAInspect
Get a comprehensive overview of what Sequencer is, including its value proposition, target audience, and key differentiators. No authentication required.
Inputs: no named parameters.
get_pricing_infoBInspect
Get pricing information including subscription tiers, credit costs, and billing FAQs. No authentication required.
Inputs: tier.
get_production_statusBRead-onlyIdempotentInspect
Read production generation progress and output media IDs, including any failed shots.
Inputs: runId (required), workspaceId (required).
get_production_templateBRead-onlyIdempotentInspect
Read a production template or one of its immutable versions.
Inputs: templateId (required), workspaceId (required), version.
get_project_runARead-onlyIdempotentInspect
Get compact, refreshed status and timing for a saved project run. Returns completed, active, failed and waiting jobs without prompts or histories.
Inputs: runId (required), editId (required), workspaceId (required).
get_proposalAInspect
Get the current proposal content for an edit. Returns full markdown for context plus the proposal summary and full-proposal link. Show a short summary and link in chat; show full markdown only if requested. Approval can happen in chat using set_proposal_status.
Inputs: editId (required), workspaceId (required), proposalId.
get_remotion_layer_guideAInspect
Get the contract, supported APIs, and example for creating custom React animation layers.
Inputs: no named parameters.
get_sceneCInspect
Get detailed information about a specific scene.
Inputs: editId (required), sceneId (required), workspaceId (required).
get_sequencer_capabilitiesAInspect
Call this first when deciding whether Sequencer can help with a user request. It maps common user intents and model aliases to the right Sequencer MCP tools, including image, video, audio, music, storyboard, edit, workspace, and media workflows.
Inputs: no named parameters.
get_sequencer_skillLoad Sequencer skillARead-onlyIdempotentInspect
Load instructions selected from list_sequencer_skills. Public workflows need no sign-in. Personal skills (my- IDs) require authentication and are read only from the current account. User-authored instructions remain subject to tool permissions and production approvals. Generates no media.
Inputs: skillId (required).
get_server_infoCInspect
Get information about this MCP server and its capabilities.
Inputs: no named parameters.
get_shotAInspect
Get a shot by its ID or its one-based number in the edit, in scene then shot order. Returns the selected start frame and settings for a shot image retake.
Inputs: editId (required), workspaceId (required), shotId, shotNumber, +1 more.
get_storytelling_guideCInspect
Get a comprehensive storytelling framework guide for creating compelling narratives.
Inputs: framework.
get_subscription_helpBInspect
Get help with subscription management including upgrading, downgrading, canceling, and payment issues. No authentication required.
Inputs: action.
get_support_faqAInspect
Get frequently asked support questions and answers. Use this to help users with common issues. No authentication required.
Inputs: topic.
get_text_presetsAInspect
Get the available text overlay presets. Each preset provides a complete styling template (font, color, animations, position) for common text overlay styles like cinematic titles, lower-thirds, subtitles, breaking news, etc. Use the preset ID with add_text_overlay to quickly create styled text.
Inputs: no named parameters.
get_usage_guideAInspect
Get the current usage guide for the Sequencer MCP server, including authentication, tool categories, generation workflows, and response conventions. Use this when integrating a new MCP client or when an agent is unsure how to operate Sequencer.
Inputs: no named parameters.
get_video_prompt_guideAInspect
Get comprehensive guidance on writing effective AI video generation prompts.
Inputs: no named parameters.
get_workflowAInspect
Read the editable workflow graph, including exact existing node sockets, data and connections. Run history is omitted by default; use includeExecutionState only to diagnose execution.
Inputs: workflowId (required), workspaceId (required), includeExecutionState.
get_workflow_building_guideAInspect
Get comprehensive guidance on building node-based workflows, including available node types, socket connections, and common workflow patterns. CALL THIS FIRST when building complex workflows.
Inputs: pattern.
get_workflow_summaryBInspect
Get a human-readable summary of a workflow's structure and data flow.
Inputs: workflowId (required), workspaceId (required).
get_workspaceBInspect
Get detailed information about a specific workspace including member count.
Inputs: workspaceId (required).
get_world_code_workspaceARead-onlyIdempotentInspect
Open a private staged coding workspace for a Worldstream. Returns a file index with hashes, no duplicated source. Read/search files, patch exact text, validate, inspect real desktop/mobile screenshots and controls, then save the verified draft. Existing worlds remain unchanged until save. For new worlds choose a Genesis starter. Workspaces expire after 24 hours.
Inputs: workspaceId (required), starter, liveWorldId.
get_world_commerceBRead-onlyIdempotentInspect
Read host-owned paid Genesis offers, fixed gem prices and catalog revision. Prices and wallets stay outside genesis.json and controller code. Interfaces display Genesis.commerce.offers() and call Genesis.commerce.purchase(offerId, userInput); the platform confirms and charges, then the controller receives purchase.completed with a verified transactionId, offerId, gems and payload. Failed deliveries refund automatically. Ordinary Genesis.action cannot submit a registered paid action.
Inputs: liveWorldId (required), workspaceId (required).
get_world_experienceBRead-onlyIdempotentInspect
Read world settings, current version, input bindings, interface source and connected games before editing. Existing game references are pinned to immutable versions. Read each connected game before editing it; preserve other worlds pinned versions.
Inputs: liveWorldId (required), workspaceId (required).
import_media_from_urlAInspect
Import a publicly reachable image, video, or audio URL into Sequencer workspace media and return a mediaId. Use this when a file is already hosted at an HTTP(S) URL. Local disk paths such as C:/... are not reachable by the MCP server; use upload_media_base64 or the REST /v1/upload endpoint for local files.
Inputs: sourceUrl (required), workspaceId (required), fileName, folderId, +3 more.
inspect_edit_frameAInspect
Render and inspect the final composed frame of an edit at an exact timeline time. This is the fast visual spot-check tool for typography, overlays, framing, style consistency, transition boundaries, and whether the picture matches the intended beat. It renders the real timeline composition without exporting the entire video or mixing audio. Use watch_video or review_edit when motion, pacing, or sound must be judged across time.
Inputs: editId (required), workspaceId (required), timestampSeconds (required).
inspect_hosted_world_siteARead-onlyIdempotentInspect
Review a saved hosted site draft using real desktop and mobile screenshots plus layout, visible control, image and runtime diagnostics. Use once near the end of a new build or substantial redesign. Fix clear issues, then use at most one follow-up review on the affected page. Skip for small copy or metadata edits. Pass the exact saved versionId and an optional existing page with query/hash. Uses the real site iframe bridge; experience players are labelled placeholders, sessions and paid effects are disabled. Does not save or publish.
Inputs: worldId (required), workspaceId (required), expectedVersionId (required), page.
inspect_storyboardAInspect
Build one ordered contact sheet from every completed shot starting frame in an edit and load it into visual context. Use this after storyboard image generation and before the first shot video. Judge the sequence as a whole for continuity, composition, defects, style, full-bleed framing, shot variety, and duration rhythm. Re-run it after changing a shot image, shot order, or timing.
Inputs: editId (required), workspaceId (required).
inspect_world_code_workspaceARead-onlyIdempotentInspect
Render the actual staged Genesis app at desktop or mobile size. Returns image pixels, accessible controls, public state, console errors, overflow and hit-target diagnostics. Execute bounded click/fill/key interactions or controller actions as preview players. Use observed names/selectors, not invented controls. Inspect then replay a scenario with steps; each call starts fresh. Fixtures are explicit simulated tool results, never paid generation. For scene.request/image.request fixtures supply provider fields, with imageUrl:fixture://image and videoUrl:fixture://video for built-in simulated media; tool.* fixtures supply structured data. Assertions check public state or visible controls. Fix failures and repeat only affected checks. No database, publication or paid-media effects.
Inputs: viewport (required), workspaceId (required), codeWorkspaceId (required), steps, +2 more.
link_live_avatar_to_worldstreamADestructiveInspect
Link an existing workspace avatar to a Worldstream draft. Read the world first and supply expectedVersionId. Preserves the interface, controller and other avatar links. Does not publish.
Inputs: characterId (required), liveWorldId (required), workspaceId (required), expectedVersionId (required).
lip_sync_video_mediaAInspect
Run lip sync on a video media item using a supplied audio URL. Keeps the original playable and saves the completed result as a new version when the source is still current.
Inputs: mediaId (required), modelId (required), audioUrl (required), workspaceId (required), +2 more.
list_assetsCInspect
List assets in a workspace. Can filter by type (character, location, prop).
Inputs: workspaceId (required), type, limit.
list_audio_tracksBInspect
List all audio timeline tracks in an edit, with resolved audio media URLs/status when available.
Inputs: editId (required), workspaceId (required).
list_available_nodesAInspect
List all node types available for building workflows. Use get_node_definitions for detailed schema.
Inputs: category.
list_editsCInspect
List all edits (projects) in a workspace.
Inputs: workspaceId (required), limit.
listen_to_audioAInspect
Return a completed audio item URL and measured metadata. This tool returns text, not audio input to the model. Auditory review requires a separate audio-capable client tool.
Inputs: mediaId (required), workspaceId (required).
list_experience_gamesBRead-onlyIdempotentInspect
List saved playable games in a workspace, with playtest links and current version IDs.
Inputs: workspaceId (required).
list_exportsBInspect
List prior exports for an edit, including status, format, version index, URLs, and export settings.
Inputs: editId (required), workspaceId (required), limit, includeDiagnostics.
list_foldersCInspect
List folders in a workspace.
Inputs: workspaceId (required), parentFolderId.
list_hosted_world_experiencesBRead-onlyIdempotentInspect
Read real workspace avatars, games, apps and Worldstreams with exact catalog IDs, readiness and attachment state. Use existing built experiences before designing their pages. Returns public card metadata only. Never invent avatar IDs or simulate their players.
Inputs: worldId (required), workspaceId (required).
list_hosted_worldsARead-onlyIdempotentInspect
List hosted sites in the active workspace to resolve a world title before editing. Hosted world IDs are separate from Worldstream liveWorldIds.
Inputs: workspaceId (required).
list_live_avatarsBRead-onlyIdempotentInspect
List existing live conversational avatars before creating or editing one. Reuse the requested character ID to avoid duplicates.
Inputs: workspaceId (required).
list_live_avatar_voicesBRead-onlyIdempotentInspect
Read the actual live-avatar preset voice catalog. Match voice language, accent and delivery from returned metadata; never invent IDs. Optional search filters metadata.
Inputs: workspaceId (required), limit, search.
list_mediaCInspect
List media objects in a workspace. Can filter by type (image, video, audio) and status.
Inputs: workspaceId (required), type, limit, status.
list_overlay_itemsBInspect
List all overlay items in a specific overlay track. Returns full item details including text config, position, timing, and animations.
Inputs: editId (required), trackId (required), workspaceId (required).
list_overlay_tracksBInspect
List all overlay tracks in an edit. Overlay tracks contain text, image, and video items layered on top of the main video timeline.
Inputs: editId (required), workspaceId (required).
list_production_templatesBRead-onlyIdempotentInspect
List reusable production templates in a workspace.
Inputs: workspaceId (required).
list_scenesAInspect
List all scenes in an edit, ordered by sequence.
Inputs: editId (required), workspaceId (required).
list_sequencer_skillsDiscover Sequencer skillsARead-onlyIdempotentInspect
Find workflows for architectural walkthroughs, short films, avatar explainers, product animations, ad variations, product photography, static ads, thumbnails, branding, logo animation, reframing and videos from webpages or articles. Use for these outcomes even when the request does not name Sequencer. Returns workflow IDs, descriptions, required inputs and tools. Load the selected workflow with get_sequencer_skill. Includes the signed-in account’s personal skills with source personal and my- IDs. Read-only; creates no projects or media.
Inputs: no named parameters.
list_shotsBInspect
List all shots in an edit, optionally filtered by sceneId. Shots reference media objects instead of embedding generation data.
Inputs: editId (required), workspaceId (required), sceneId.
list_voicesAInspect
List actual Cartesia voice IDs with names, gender, languages, and accents. Resolve narration preferences with this catalog before choosing voiceId. Delivery instructions alone do not select a Cartesia voice.
Inputs: workspaceId (required), name, limit, gender, +2 more.
list_workflowsCInspect
List all workflows in a workspace.
Inputs: workspaceId (required), limit.
list_workspace_membersBInspect
List all members of a workspace, including their roles and emails.
Inputs: workspaceId (required).
list_workspacesAInspect
List accessible workspaces with the personal default first. Increase limit when hasMore is true to see more workspaces. Use this when the user asks to choose, inspect, or connect a Sequencer workspace, or when a non-generation tool requires workspaceId. For standalone generate_image, generate_video, and generate_audio calls, do not call this just to find a workspace; omit workspaceId and Sequencer will use the default workspace.
Inputs: limit.
list_world_experiencesCRead-onlyIdempotentInspect
List saved world experiences and the default Genesis package contract in the active workspace.
Inputs: workspaceId (required).
move_item_to_folderBInspect
Move a media, edit, or asset item to a folder (or to root by passing null folderId).
Inputs: itemId (required), itemType (required), workspaceId (required), folderId.
move_overlay_item_to_trackAInspect
Move an overlay item from one overlay track to another, preserving all timing, transform, animation, and styling data.
Inputs: editId (required), itemId (required), workspaceId (required), sourceTrackId (required), +1 more.
move_shot_to_sceneBInspect
Move a shot from one scene to another, optionally setting its order in the target scene.
Inputs: editId (required), shotId (required), workspaceId (required), targetSceneId (required), +1 more.
open_paywallAInspect
Open the paywall or subscription upgrade modal. Use this when an action requires a Pro subscription (e.g. generating certain media) and the user is not subscribed. In Sequencer/Spark, the frontend will show the upgrade modal. In external MCP clients, this tool cannot open Sequencer UI; give the user the Sequencer app URL and explain they need to upgrade there.
Inputs: reason (required).
open_sequencer_workspaceSequencer StudioARead-onlyInspect
Open the Sequencer workspace browser to view projects, recent creations, and shot previews. Read-only. Creation starts only after a user chooses a task and approves its plan and cost.
Inputs: workspaceId, startingTask.
prepare_hosted_world_assetAInspect
Optimize an uploaded or completed generated workspace asset for a hosted world. Pins original bytes, creates WebP/AVIF delivery sizes and returns the full asset manifest entry. Reuse this entry in site assets. Does not generate paid media or publish. Use panorama=true for 360-degree textures.
Inputs: path (required), worldId (required), workspaceId (required), mediaId, +2 more.
prepare_live_avatarAInspect
Prepare the saved avatar through the same Anima pipeline as the character manager. Use its returned status and get_live_avatar to check progress. Never repeatedly prepare a queued/running avatar or claim a speaking test occurred. Does not start a paid call.
Inputs: characterId (required), workspaceId (required).
quote_generationQuote Generation CostARead-onlyIdempotentInspect
Get a read-only USD quote for an image, video, or audio generation. Use it to build an initial project estimate or check a job against an existing budget. Select an exact model ID from get_model_catalog and specify all billable settings. Reports usage-based estimates and missing inputs explicitly. Creates no media and spends no credits.
Inputs: model (required), count, goFast, duration, +12 more.
quote_live_avatar_sessionARead-onlyIdempotentInspect
Quote a bounded live video conversation in USD without starting it. Video streaming and background image generation have separate Genesis budgets.
Inputs: characterId (required), workspaceId (required), maxSessionSeconds (required).
read_world_code_fileARead-onlyIdempotentInspect
Read up to 400 numbered lines from one staged project file, bounded to 12 KB. Returns its current hash for exact patches. Default reads 160 lines. Follow nextRead (startLine/startColumn) to read omitted source, including long minified lines. Never guess omitted code.
Inputs: path (required), workspaceId (required), codeWorkspaceId (required), endLine, +2 more.
regenerate_shot_imageADestructiveInspect
Regenerate the starting image of an existing shot as the next version. Keeps the same shot and image media IDs, preserves previous versions, and selects the new image in the shot on success. Use this for a shot retake or revised shot image. May spend Sequencer credits.
Inputs: editId (required), shotId (required), workspaceId (required), model, +14 more.
remove_image_backgroundremove image backgroundADestructiveInspect
Remove an image background using a catalog model that supports remove_background. The selected model determines transparency support. Use get_model_catalog to choose a supported model and its settings. Returns a tracked task and playable result when complete.
Inputs: model (required), sourceMediaId (required), prompt, maxCostUsd, +18 more. Returns: data, error, success
remove_video_backgroundremove video backgroundADestructiveInspect
Remove a video background when an active catalog model supports remove_background and video input. Select an alpha-capable output format in modelSettings when supported. Use get_model_catalog to choose a supported model and its settings. Returns a tracked task and playable result when complete.
Inputs: model (required), sourceMediaId (required), prompt, maxCostUsd, +18 more. Returns: data, error, success
remove_video_background_mediaAInspect
Remove the background of a workspace video with Bria. Exports transparent WebM or ProRes MOV, with optional original audio.
Inputs: mediaId (required), workspaceId (required), modelId, videoUrl, +4 more.
render_imageShow Sequencer imageARead-onlyIdempotentInspect
Use this after get_media reports that a Sequencer image is completed. It displays completed image media inline in the conversation.
Inputs: mediaId (required), workspaceId (required). Returns: data, error, success
render_mediaView MediaARead-onlyIdempotentInspect
Display images, videos, audio and completed MP4 project exports in the inline player. For project exports first poll get_export to completed, then pass its exact renderMediaArgs. For workspace media pass the returned media IDs. The player monitors queued and generating workspace media. Do not replace this tool with Markdown or HTML video embeds.
Inputs: mediaId (required), workspaceId (required), additionalMediaIds. Returns: data, error, success
reorder_shotsBInspect
Bulk reorder shots within an edit. Efficiently updates all shot order values in a single batch write.
Inputs: editId (required), shotOrders (required), workspaceId (required).
request_asset_reviewAInspect
Request the user to review and approve/reject specific assets. For external MCP clients, returns inlineReview assets with image URLs/markdown that should be shown directly in chat; reviewUrl is only a secondary Sequencer link. In Spark, the in-app review modal may still open. Recommended after the initial character/location pass in a proposal build before expensive shot generation; optional for later incremental edits or explicit user-directed asset creation.
Inputs: editId (required), assetIds (required), workspaceId (required).
request_loginAInspect
Request the user to log in or register to continue. Use this when an action requires authentication and the user is not logged in. In Sequencer/Spark, the frontend will show a login modal and resume after login. In external MCP clients such as Codex, Claude Desktop, Claude Code, or Antigravity, this tool cannot open a modal; tell the user to reconnect or re-authorize the Sequencer MCP server instead, and do not claim a modal opened.
Inputs: reason (required).
review_editAInspect
Export and analyze the current edit, then return a structured video review report. Prefer this over watch_video when the user asks to watch, review, analyze, or improve a film. The backend handles video analysis and returns provider-agnostic JSON with issues and recommended edit actions.
Inputs: editId (required), workspaceId (required), mode, focus.
run_production_templateADestructiveInspect
Generate a saved production template into a new editable Sequencer project. Each run spends credits and has tracked output tasks. Poll get_production_status. To rerun, call again; previous projects remain preserved.
Inputs: templateId (required), workspaceId (required), version, parameters, +1 more.
run_video_workflowCInspect
Run a Sequencer workflow API endpoint from the video editor context. Inputs can include video/audio/image URLs and arbitrary scalar fields.
Inputs: inputs (required), workflowId (required), workspaceId (required).
save_experience_gameAInspect
Build ONLY a game whose current proposal was approved by the user. Read get_experience_game, follow its approved proposal, and pass proposalRevision and expectedVersionId. Supply organized files (index.html, styles.css, scripts/*.js, optional JSON/docs) with local stylesheet/classic script references, or one complete HTML source. Use ordered classic scripts and shared namespaces, no imports/requires. The server bundles code to a single playable HTML under 256 KB and stores the editable package separately (up to 64 files / 1 MB). Media belongs in existing asset:// IDs, canvas or inline art. Include responsive start, pause, help, score/progress, win/loss and restart UI plus keyboard/touch controls. External URLs, network APIs, workers, embeds, eval, and parent access are blocked. Match the approved worldId. Returns the Games tab playtest link. Never paste implementation code in the chat.
Inputs: title (required), gameId (required), description (required), workspaceId (required), +7 more.
save_experience_game_proposalAInspect
FIRST step for creating or revising a game. Save a proposal document and a visible Games tab entry, then STOP for human approval. Markdown must have headings starting Concept, Gameplay, Controls, Screens, Files, and Playtest. Describe audience, objective/core loop/levels/win/loss, desktop/touch controls, visual/audio direction, start/pause/help/score/game-over/restart UI, code organization and assets, and concrete checks. Do not include game code. For an existing game read it first and pass expectedVersionId and expectedProposalRevision. For a modular Worldstream attachment supply worldExperienceTarget with its liveWorldId, inputBindingId, and current expectedVersionId. An approved build automatically pins the new game version only if that world version is still current. A revised proposal always needs fresh approval.
Inputs: title (required), description (required), workspaceId (required), proposalMarkdown (required), +6 more.
save_hosted_world_siteAInspect
Save one versioned hosted site draft. Read get_hosted_world first and pass expectedVersionId (null for its first site). Supply the complete site files. Concurrent edits fail without overwriting. Use the hosted-world skill and SDK for attached experiences. This does not publish, start paid generation, change attachments or set prices. Optional metadata changes only title, URL and description.
Inputs: site (required), worldId (required), workspaceId (required), expectedVersionId (required), +1 more.
save_production_templateBDestructiveInspect
Save a versioned production template for product ads, 3 to 5 shot stories, or image localization. Templates use {{parameter}} placeholders and produce editable projects when run.
Inputs: definition (required), workspaceId (required), templateId.
save_proposalAInspect
Save a proposal document for user review before implementing a complex project. The proposal MUST include a Models section listing the friendly names of the planned image/still and video models, a "💰 Estimated Cost" section with one estimated USD total and a spending ceiling for the planned project, and a concrete numbered scene/shot or beat list. Default project models are Nano Banana 2.1 (google-nano-banana-2-1) for character/location/shot still images and Gemini Omni 1.2 Flash (google-gemini-omni-1-2) for videos after still-image approval. Keep those raw IDs in tool arguments and use friendly model names in user-facing proposal text. Do not use source-file references such as "from script.md" or vague language such as "approximately X shots" instead of enumerating the planned work. Save the complete proposal but show only a short summary in chat, including models, cost and approval scope. Provide a View full proposal link using the returned reviewUrl and ask for approval or changes in chat. Use native question controls only when the host provides an approval-capable tool. Never require clicking approval in Sequencer or fabricate buttons. Open the link only when the user requests it.
Inputs: editId (required), workspaceId (required), proposalMarkdown (required), threadId, +3 more.
save_world_code_workspaceAInspect
Save the current staged package as one verified Worldstream draft. Requires current validation, passing desktop/mobile inspections and at least one exercised custom control. Checks the original world version so concurrent editor changes are preserved. On a conflict open the latest world and reapply only requested changes, never force overwrite. Saving never publishes.
Inputs: workspaceId (required), codeWorkspaceId (required), expectedRevision (required).
save_world_experienceAInspect
Save a versioned draft world, settings and optional custom interface together. Read get_world_experience before editing and pass its versionId as expectedVersionId. Omit liveWorldId only for a new world. Provide project as the portable genesis.json manifest, with interfaceSource and controllerSource. Keep Worldstreams listing, avatar connections and chat access/moderation in settings. The existing definition argument is supported for older clients. New worlds use a unified Genesis package: local HTML/CSS/classic JS interface using window.Genesis, optional pure onEvent controllerSource, typed actions, input windows and authorized tool effects. Read get_genesis_sdk before authoring. Generated UI images use asset://ID references declared in interfaceAssets:[{id,mediaId}]. The server verifies completed workspace images and pins them with this version. Covers use project.coverImageUrl from completed generate_image media. Preview stage artwork uses the separate previewImageUrl field. Omit it to preserve or set an empty string to remove. Build responsive interfaces for touch/mobile and web. No direct external URLs, networking, parent access or eval. Reuse game packages by pinning gameId and versionId in gameBindings; game edits use the existing game proposal workflow. This does not publish or start generation. Return the saved world and preview link.
Inputs: workspaceId (required), project, settings, definition, +8 more.
scrape_urlAInspect
Read a public HTML web page and return its visible text, metadata, and direct image URLs. Use this only when the user supplies a webpage URL whose content or images must inform a Sequencer project. Do not use it for media files, JSON, waveform URLs, or internal generation output. Use get_media and listen_to_audio for generated audio. This does not render client-side JavaScript and does not import or generate media.
Inputs: url (required), imageLimit.
search_workspaceAInspect
Search existing workspace media by prompt, file name, description, and tags. This searches metadata, not image pixels. Use a concise subject keyword such as "cat". Follow nextCursor until hasMore is false when the user asks for all matches. Never create an edit while searching.
Inputs: query (required), workspaceId (required), type, limit, +1 more.
search_world_codeARead-onlyIdempotentInspect
Search literal text across staged project files. Returns numbered matches and pagination. Use this to locate CSS, handlers and controller rules before focused reads and patches.
Inputs: query (required), workspaceId (required), codeWorkspaceId (required), path, +1 more.
send_live_avatar_messageAInspect
Send a typed question into an active avatar session, sharing its voice conversation. The session spending and duration limits still apply.
Inputs: message (required), workspaceId (required), avatarSessionId (required).
set_asset_approval_statusAInspect
Approve, reject, or reset one or more assets from chat. External MCP clients should call this after showing inline asset images/descriptions and receiving user approval or revision feedback, instead of requiring the user to open Sequencer.
Inputs: status (required), assetIds (required), workspaceId (required), note, +1 more.
set_proposal_statusAInspect
Approve, reject, or reset a saved proposal. Use this in external MCP clients when the user approves or rejects a proposal in chat, so the Sequencer edit state stays in sync without relying on a Spark-only UI modal.
Inputs: editId (required), status (required), workspaceId (required), note, +3 more.
setup_projectAIdempotentInspect
Atomically create a project with ordered scenes, shots, exact supplied-media mappings, timing, style and existing audio tracks. Or append structure to an existing edit. Validate everything before writing. No media generation or approval occurs. Reuse idempotencyKey on retries to return the original IDs.
Inputs: title (required), aspectRatio (required), workspaceId (required), idempotencyKey (required), +6 more.
set_world_commerceAInspect
Register or replace paid Genesis offers after saving the world. Read get_world_commerce and get_world_experience first. Pass both current revision fields. Each offer links to a declared actionId with fixed payload fields and optional user-editable inputFields. Use whole gem prices explicitly requested by the creator. availability:live grants signed-in viewers access during an active continuous stream independently of battle input windows. fulfillment:video reserves payment through asynchronous preparation until actual scene playback completes. Controller handlers grant benefits only on purchase.completed using event.data.payload. This changes live host pricing and does not purchase or start generation.
Inputs: offers (required), liveWorldId (required), workspaceId (required), expectedRevision (required), +1 more.
split_shotAInspect
Split a shot into two adjacent shot records at a time offset from the shot start, preserving media refs and playback metadata.
Inputs: editId (required), shotId (required), splitTime (required), workspaceId (required).
start_live_avatar_sessionAInspect
Start a paid live video conversation after an explicit user request. Requires maxCostUsd and maxSessionSeconds. Rejects a reservation above the cost limit or an unprepared avatar. Voice and text use one conversation. Keep avatarSessionId to send messages and stop.
Inputs: maxCostUsd (required), characterId (required), workspaceId (required), maxSessionSeconds (required), +2 more.
stop_live_avatar_sessionADestructiveInspect
Stop an avatar session and settle connected-time billing, returning unused reservation. Repeated stops return the settled result.
Inputs: workspaceId (required), avatarSessionId (required).
trigger_auto_layoutAInspect
Trigger automatic layout of nodes in the workflow. This arranges nodes left-to-right based on data flow. Call this after adding all nodes and connections.
Inputs: workflowId (required), workspaceId (required).
update_assetCInspect
Update an existing asset.
Inputs: assetId (required), workspaceId (required), name, description, +2 more.
update_audio_trackCInspect
Update an audio timeline track: placement, trim, fades, volume, keyframes, channel, and shot pinning.
Inputs: editId (required), trackId (required), workspaceId (required), volume, +12 more.
update_editBInspect
Update an existing edit (project). Supports partial updates — only provided fields are changed.
Inputs: editId (required), workspaceId (required), style, title, +10 more.
update_hosted_world_experiencesAInspect
Attach existing ready workspace experiences or detach selected IDs from a hosted world. Use exact catalog IDs from list_hosted_world_experiences. Changes merge atomically and preserve other attachments. This does not edit, generate, start, charge for or publish experiences. Only creator-side authenticated tools can change the lineup.
Inputs: worldId (required), workspaceId (required), attachIds, detachIds.
update_live_avatarADestructiveInspect
Read the existing avatar first, then update only requested settings. Preserves omitted settings, assets and publication status. Image, voice or mode changes may require preparation. Does not publish or start calls.
Inputs: characterId (required), workspaceId (required), name, cerebro, +16 more.
update_media_tagsAInspect
Add, remove, or replace searchable tags on an existing workspace media item. Use only when the user asks to tag or retag media. This updates metadata; it does not tag an asset into an edit shot.
Inputs: tags (required), mediaId (required), workspaceId (required), mode.
update_nodeCInspect
Update a node configuration.
Inputs: config (required), nodeId (required), workflowId (required), workspaceId (required).
update_overlay_itemCInspect
Update an existing overlay item. Can change text, position, timing, animation, opacity, and more.
Inputs: editId (required), itemId (required), trackId (required), workspaceId (required), +46 more.
update_overlay_trackBInspect
Update overlay track metadata: name, stack order, visibility, and lock state.
Inputs: editId (required), trackId (required), workspaceId (required), name, +3 more.
update_proposalCInspect
Update an existing proposal to track execution progress.
Inputs: editId (required), workspaceId (required), proposalId, sourceMedia, +4 more.
update_sceneCInspect
Update an existing scene.
Inputs: editId (required), sceneId (required), workspaceId (required), name, +2 more.
update_shotBInspect
Update an existing shot. Can change scene, order, timing, media refs, dialogue, motion prompt, and tagged assets. Only provided fields are changed.
Inputs: editId (required), shotId (required), workspaceId (required), order, +18 more.
update_shot_media_refBInspect
Update a specific shot media ref by matching mediaId and optional role. Can change role, order, mediaId, and version override.
Inputs: editId (required), shotId (required), mediaId (required), workspaceId (required), +6 more.
update_transitionBInspect
Update one timeline transition by transitionId or boundaryId.
Inputs: editId (required), workspaceId (required), type, duration, +6 more.
update_workspaceCInspect
Update a workspace. Only the workspace owner can update.
Inputs: workspaceId (required), icon, color, title.
upload_media_base64AInspect
Upload a local image, video, or audio file into Sequencer by passing base64 file contents. This is the MCP-native local-file path when the client can read the file bytes. For large videos, prefer the REST /v1/upload multipart endpoint to avoid MCP payload limits.
Inputs: fileName (required), mimeType (required), base64Data (required), workspaceId (required), +2 more.
upscale_imageupscale imageADestructiveInspect
Upscale an existing image using a catalog model that supports upscale_image. Use get_model_catalog to choose a supported model and its settings. Returns a tracked task and playable result when complete.
Inputs: model (required), sourceMediaId (required), prompt, maxCostUsd, +18 more. Returns: data, error, success
upscale_videoupscale videoADestructiveInspect
Upscale an existing video using a catalog model that supports upscale_video. Use get_model_catalog to choose a supported model and its settings. Returns a tracked task and playable result when complete.
Inputs: model (required), sourceMediaId (required), prompt, maxCostUsd, +18 more. Returns: data, error, success
validate_hosted_world_siteARead-onlyIdempotentInspect
Compile the complete local HTML/CSS/JavaScript site package without saving, publishing or paid effects. Returns build diagnostics. Local modules and HTML pages are supported; HTTPS imports stay browser-only. Use window.HostedWorld to mount or open attached experiences.
Inputs: site (required).
validate_production_templateARead-onlyIdempotentInspect
Render a template with parameters and estimate generation cost without spending credits. Missing price data is reported explicitly.
Inputs: templateId (required), workspaceId (required), version, parameters.
validate_world_code_workspaceBRead-onlyIdempotentInspect
Run the same schema, source, sandbox and controller checks used by saving on this staged revision. Correct diagnostics with focused patches. Visual and behavioral verification is separate.
Inputs: workspaceId (required), codeWorkspaceId (required).
validate_world_experienceARead-onlyIdempotentInspect
Validate a complete experience definition and optional custom interface code without saving or starting paid generation. Input types: text, vote, voice, image, click, game. Declare interface.handledInputBindingIds for custom controls; uncovered inputs retain standard controls. Overlay regions use {x,y,width,height} fractions within the stage. New Genesis controls use window.Genesis.action(actionId,data) and actions.get(id).canSubmit. Custom controllers use function onEvent(context). Read get_genesis_sdk for the exact contract and examples. Use the existing definition contract from get_world_experience or list_world_experiences. Return diagnostics and normalized settings.
Inputs: project, definition, interfaceFiles, interfaceAssets, +4 more.
watch_videoAInspect
Export the current project as a low-quality review video and return its URL for AI analysis. Use this when the user explicitly asks to watch, review, or analyze the project, or when the user approved video generation for an active finished-video skill that requires a final review-and-edit pass. The video is exported at 480p/15fps for fast, cost-efficient viewing. Returns a video URL that the agent should fetch and inspect before applying concrete edit fixes.
Inputs: editId (required), workspaceId (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Generate images, video and audio with a price estimate and project budget controls.
Create and edit images and video, generate music, and retrieve existing audio projects.
Generate and edit images, create videos, quote credit costs, and retrieve private results.
Generate images, videos and music with model discovery, cost estimates and asynchronous results.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceHosted MCP server (OAuth, no API keys) that makes short drama series (micro-dramas, sitcoms, K-drama style, any language) and other short vertical videos from Claude, ChatGPT or Codex, with the same cast every episode.1Apache 2.0
- AlicenseNot gradedqualityDmaintenanceGenerate and refine AI images/audio/video through natural conversation.412Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables AI clients to list video models, get exact credit quotes, upload images, start renders, and retrieve MP4 links for turning photos or text prompts into short AI videos.MIT

Popcraft MCPofficial
AlicenseNot gradedqualityBmaintenanceEnables AI agents and MCP clients to generate and edit video, images, 3D, music, and sound effects, upload or reuse media, preview credit costs, and follow production workflows through a single hosted connector.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.