Connect Twelver's native toolsets to any MCP-compatible client.
Ready pages for Claude, Cursor, web search and media generation.
Ready-made MCP servers — each exposing tools your agent can call.
Generate, edit, and transform images directly from your AI agent.
Generate, edit, and transform images using Grok's native vision models.
BytePlus Seedream — text-to-image, image-to-image, multi-image blends, and batch generation.
Ideogram — best-in-class in-image text rendering: generate (incl. transparent PNGs), remix, prompt-based edit (incl. extend/reframe), and background removal.
Generate and animate videos from text or images using Grok's advanced video model.
Seedance 2.5 — video with sound up to 30 s from text, images or references, plus edit and extend. Each clip is a 480p draft first; approve it to get the 1080p final.
Seedance 2.0 mini — cheaper video with sound up to 15 s at 480p or 720p: text, image, references, edit and extend.
Google Veo 3.1 (Gemini) — high-fidelity 720p–4K video with native audio: text/image-to-video, first→last-frame interpolation, reference images, and extend.
MiniMax H3 — up to 15s at 2K with native audio: text, image, first-and-last-frame, and reference-driven video.
Alibaba HappyHorse — text/image/multi-reference video generation, plus instruction-driven video editing.
Alibaba Wan 3.0 — clips up to 30s from text, images or multi-reference (images, video, voice) with native audio, plus instruction-driven editing and extension.
Stitch, trim, crop, and resize videos, audio, and images — fast local processing, no AI generation.
Generate music from text using Google's music model.
Generate music from text and create music covers with MiniMax.
Gemini TTS — text-to-speech, multi-speaker dialogue, and custom voice design.
Qwen TTS — text-to-speech and voice cloning.
Grok TTS — expressive speech in 28 voices with laughs, whispers and pauses, the same voices as live calls.
Transcribe audio and video files into text.
Real-time web search and crawling to get up-to-date information from the internet.
Find images that already exist on the web through the Yandex Images index — by description, with format, size, orientation and colour filters, or in reverse: upload a picture and see where else it appears online.
Long-form documents and spreadsheets, written and edited by your agent: articles, reports, essays and briefs in Markdown, plus tabular data. Code, sites, presentations and downloadable graphics each have their own toolset now, so an agent that writes reports no longer carries the instructions for designing posters.
Code snippets written by your agent and shown in their own panel beside the chat, where you can read, copy and re-save them. Python runs; other languages are written but not executed.
Interactive websites and web apps built by your agent as one self-contained HTML page — landing pages, dashboards, calculators, small tools. They render live beside the chat, and every one has a link you can share.
Slide decks built by your agent: 16:9 slides (or 9:16 vertical) with navigation, a fullscreen present mode, a shareable link, and a PDF export that puts one slide on each page.
Downloadable graphics designed by your agent — posters, social cards, infographics, quote cards, badges and marketplace cards — laid out on a fixed canvas and saved as a PNG. Every graphic is rendered in a real browser and checked the moment it is saved, so what comes back is measured rather than guessed. Paired with Ideogram, transparent cutouts stack into a graphic as layers, applique-style.
Orchestrate sub-agents from within your AI agent workflows.
Clients that support OAuth (like Claude) don't need an API key. Just paste the URL and sign in.
No keys: paste the URL into your client and sign in — Claude, Cursor and any other OAuth client.
Copy the connector URL
Paste it into your MCP client
Sign in via OAuth — done
Check the tools — URLs and config update themselves.
Image Generation (Nano Banana)
https://twelver.ru/api/mcp/v1/image-generationVideo Generation (Seedance)
https://twelver.ru/api/mcp/v1/seedance-video-generationMusic (MiniMax)
https://twelver.ru/api/mcp/v1/minimax-musicWeb Search
https://twelver.ru/api/mcp/v1/web-search{
"mcpServers": {
"twelver-image-generation": {
"url": "https://twelver.ru/api/mcp/v1/image-generation"
},
"twelver-seedance-video-generation": {
"url": "https://twelver.ru/api/mcp/v1/seedance-video-generation"
},
"twelver-minimax-music": {
"url": "https://twelver.ru/api/mcp/v1/minimax-music"
},
"twelver-web-search": {
"url": "https://twelver.ru/api/mcp/v1/web-search"
}
}
}The same mcp.json works in LM Studio, Windsurf, Cline, VS Code and any client that reads an mcp.json.
Three steps to supercharge your AI agent with Twelver's toolsets.
Generate an API key from the Integrations menu.
Copy the MCP server URL into your config (Claude Desktop, Cursor, etc.).
Your AI agent now has access to web search, images, and more.
Connect Twelver MCP toolsets in minutes.