Claude (web)
One custom connector, sign in once. 40 tools.
Set up →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.
https://www.switchapp.ai/mcpOne custom connector, sign in once. 40 tools.
Set up →Custom connector via Developer mode (paid plans).
Set up →Native connector — no bridge, no terminal.
Set up →One claude mcp add command, then OAuth.
Set up →Add an HTTP server to ~/.codex/config.toml.
Set up →Add to .cursor/mcp.json — same endpoint, same tools.
Set up →Custom connector on grok.com. Grok Bot uses a Switch API key.
Set up →Every tool runs scoped to your Switch account over OAuth — images, video, audio, references, styles, and your whole library, straight from a chat.
Generate images across the Switch model lineup. Lock a subject, face, or product with up to 4 reference images.
Text-, image-, frame-, or reference-to-video across Kling, Seedance, WAN 2.7, MiniMax H3 Max, and Switch Video — plus motion control, omni audio-video, clip edits, and Topaz upscale.
Lip-sync a clip to audio, drive a talking-avatar video, and manage your custom voices.
Upload an image, video, or audio reference once and reuse it across generations. Image and video references sync into your live Studio reference strip.
Create and inspect persistent Editor projects, upload media directly, run the Editor agent, approve guarded paid steps, and render through HyperFrames.
One-tap photographic and cinematic looks — apply a finished style stack to your prompt without hand-tuning.
Browse folders and assets, search your library, show any asset inline, track generations, check your balance, and cancel a running task.
Say one of these to your connected AI. Each maps to a real tool.
Straight from the engine — accurate, not aspirational.
Switch Ultra and the image-edit models use your first 4 reference images.
5 or 10-second clips. Omni mode takes up to 7 image references and generates native audio.
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.
5, 10, or 15-second clips — the longest durations Switch offers.
5 or 10-second clips (text, image, or clip-edit).
Whole seconds 5 to 15 at 480p or 768p, with native audio on every clip (dialogue, ambience, lip-sync; no off switch). Text, image (start + end frame) and reference modes; reference takes up to 9 pictures, 3 clips and 3 audio files (12 total), and the reference pictures and clip seconds are billed on top of the output.
Preview. The same 5 to 15 whole seconds at 480p or 768p with native audio, about twice as fast at half the price, targeting the 97th percentile of H3 Max quality. Text and image (start + end frame) only; there is no Turbo reference lane, so reference pictures, clips and audio go through MiniMax H3 Max.
The Switch editor (HyperFrames) combines clips and renders HTML-based motion graphics into one MP4.
JSON-RPC over POST. SSE supported for long-running tool calls; clients negotiate via themcp-protocol-versionheader.
Dynamic client registration. Bearer tokens scoped per-user. API keys also supported for non-interactive clients. No raw secrets in chat.
Follows the current MCP spec. Discovery via/.well-known/oauth-protected-resource. Every tool call is logged for auditing.