Claude (web)
One custom connector, sign in once. 31 tools.
Set up →Model Context Protocol server
Plug Switch into any AI.
The Switch MCP server lets Claude, Cursor, Windsurf, and any MCP-compatible client talk directly to your Switch studio. Generate images and video, lip-sync and talking-avatar clips, reuse your reference images, search your library, and check your balance — right from the chat, no copy-paste, no tab-switching.
Endpoint
Docshttps://www.switchapp.ai/mcpChecking…·OAuth 2.1 · Streamable HTTP · 31 tools
Connect your AI
All clients →ChatGPT
Custom connector via Developer mode (paid plans).
Set up →Claude Desktop
Native connector — no bridge, no terminal.
Set up →Claude Code
One claude mcp add command, then OAuth.
Set up →Codex
Add an HTTP server to ~/.codex/config.toml.
Set up →Cursor
Add to .cursor/mcp.json — same endpoint, same tools.
Set up →What you can make
Every tool runs scoped to your Switch account over OAuth — images, video, audio, references, styles, and your whole library, straight from a chat.
Images
Generate images across the Switch model lineup. Lock a subject, face, or product with up to 4 reference images.
generate_imageexplore_models
Video
Text-, image-, frame-, or reference-to-video across Kling, Seedance, WAN 2.7, and Switch Video — plus motion control, omni audio-video, clip edits, and Topaz upscale.
generate_videolist_video_modelsget_video_statuslist_my_videos
Audio & Voice
Lip-sync a clip to audio, drive a talking-avatar video, and manage your custom voices.
lip_sync_videotalking_avatar_videovoice
References
Upload an image, video, or audio reference once and reuse it across generations. Image and video references sync into your live Studio reference strip.
upload_reference_assetget_my_active_referencesupload_media
Styles
One-tap photographic and cinematic looks — apply a finished style stack to your prompt without hand-tuning.
apply_iphone_realismapply_movie_sceneapply_high_fashion_editorialapply_cinematic_anamorphicapply_magic_hour_portraitapply_productapply_travelapply_ugcapply_wellnessapply_graphic_editorial_portrait
Library & Account
Browse folders and assets, search your library, show any asset inline, track generations, check your balance, and cancel a running task.
list_my_folderslist_my_assetssearch_my_libraryshow_mediashow_generationlist_generationscheck_job_statuscheck_balancecancel_my_task
Try these prompts
Say one of these to your connected AI. Each maps to a real tool.
Model limits
Straight from the engine — accurate, not aspirational.
Image references
Switch Ultra and the image-edit models use your first 4 reference images.
Kling v3
5 or 10-second clips. Omni mode takes up to 7 image references and generates native audio.
Seedance 2.0
5 or 10 seconds. Up to 9 image, 3 video, and 3 audio references (12 total); reference and omni modes need at least one image or video anchor.
WAN 2.7
5, 10, or 15-second clips — the longest durations Switch offers.
Switch Video
5 or 10-second clips (text, image, or clip-edit).
Stitching & motion graphics
The Switch editor (HyperFrames) combines clips and renders HTML-based motion graphics into one MP4.
Transport
Streamable HTTP
JSON-RPC over POST. SSE supported for long-running tool calls; clients negotiate via themcp-protocol-versionheader.
Auth
OAuth 2.1 + PKCE
Dynamic client registration. Bearer tokens scoped per-user. API keys also supported for non-interactive clients. No raw secrets in chat.
Spec
MCP 2025-06-18
Follows the current MCP spec. Discovery via/.well-known/oauth-protected-resource. Every tool call is logged for auditing.