Claude
- Open Add custom connector ↗
- Name it KAIROGEN and paste the URL
- Click Add, then sign in to your account
https://mcp.kairogen.ai/openai/mcp
Create images, video and audio
Create images, videos and audio with KAIROGEN from your conversation. Explore the model catalog, estimate credit costs, generate product shots, animate reference images, create reusable characters, and work with narration and voice tools. View results in interactive widgets and retrieve creations from your gallery. Connect your KAIROGEN account to use generation features and your existing credits. Available models and features depend on your account’s access.
Generate three vertical product shots of a matte black coffee tumbler on a marble counter.
https://mcp.kairogen.ai/openai/mcphttps://mcp.kairogen.ai/openai/mcpmcp.kairogen.aiThe AI reads these server instructions before using this connector, every time. From the ChatGPT store listing.
Kairogen MCP. Generate images and videos using Kairogen's full model catalog (Seedream, Flux, Nano Banana, GPT Image, Veo, Kling, Seedance, KairoClone, Topaz).
Kairogen marketing recipes (opt-in). Call ONLY if the user invokes it (asks for the marketing recipes, names a recipe, or types any /command: pass it as power, the server resolves it); never call on your own. Not invoked: do it directly. The recipes are listed in that tool.
Which tool (a model or tool the user names wins): Image from text or a photo: . Only bigger or sharper: . Video from text or a start image: . An image Kairogen generated -> video: , always with video_model (default seedance-2-0-mini). The same generation again: . The user put into an existing clip (a trend dance, a person swapped in a video), or KairoClone by name: the kairo_clone_* tools, never . Audio only (speech, sound effect, music): / / . A video's audio: add a narration -> ; translate -> ; another voice, same person -> ; re-voice a Kairogen narration -> . Status: image/video -> ; KairoClone -> ; audio job -> . History: (images, videos), (KairoClone), (audio). Characters: (use one), (create one). The user's own file: . Balance: .
Charging: , , , , , , , , , , , , and a replace or retry debit credits. Prices: , , . An ask to generate an image, video or audio is the user's go. Pass a quoted price back (expected_credits / expectedCredits). One paid call per user intent: a second version only when the user asks, after the previous one is no longer pending. Never repeat a paid call on your own after a failure, a refund, 'pending' or 'insufficient_credits'. 'insufficient_credits': nothing was generated or charged; tell the user in one sentence.
KairoClone (offer only what lists as available): transfer (Copiar movimento): the person of the images does the clip's movement; the user dancing a clip. swap (Trocar no vídeo): the clip keeps its background, light, camera, cuts, motion, mouth and audio; the cast's person becomes @Imagem N's person (face, hair, body and, by default, clothes and accessories). wardrobe (swap only): reference (default) = the photo's outfit, the clip person's glasses, watch or jacket leave; original = the clip person's outfit and accessories stay; prompt = the outfit the prompt describes. Swap prompt: only what changes, in positive words ("ela usa a blusa da @Imagem 1"); no list of NÃO, nothing that stays (the server keeps it), no clothes with wardrobe=reference. Flow: , (clip, then images), , the user's yes; a quote is the charge: with expectedCredits = its credits; . Several persons in the clip: ask whom an image replaces (cast), never pick. Set consent only once the user says they are the people in the images or authorised it. Ask quote notices even after approval: Visibility Notice: go on or change the clip (quote again); Accessory Notice: glasses or outfit leave (wardrobe=reference) or stay (original: quote again). A delivered part may carry warnings (Cast Warning, Wardrobe Warning, output, captions, unverified): show them; no refund or redo; generating again is charged. Compiled Prompt: , compiledPrompts true.
Workflow:
Not found; the server needs sign-in so there may be skills that our scan couldn't access
Create images, video and audio. Create images, videos and audio with KAIROGEN from your conversation. Explore the model catalog, estimate credit costs, generate product shots, animate reference images, create reusable characters, and work with narration and voice tools.
Open its listing in the app's connector directory and connect. Sign in to your account in the browser window that opens. It uses OAuth, so the AI never sees your password. Step-by-step setup for each app is on this page.
The KAIROGEN MCP server URL is https://mcp.kairogen.ai/openai/mcp. Paste it as a custom connector in Claude, ChatGPT, Gemini or Grok, or add it to Claude Code, Cursor or any MCP client. Setup steps.
Yes. KAIROGEN is published or run by KAIROGEN INC, so it is the official MCP server. See other official connectors.
It is listed in 1 store: ChatGPT. Apps where it is not listed can usually still add it as a custom connector.
It is ranked 14,500 of 15,719 in the ChatGPT directory. A rank is the store's own order, not a usage count. How we track ranks.
It has 58 tools: 28 read data, 11 change data and 19 can delete or overwrite data. See every tool and its inputs.
Yes. 11 tools can change data and 19 tools can delete or overwrite it. Most AI apps ask before they run these. The store marks these as destructive:
None that we found. Not found; the server needs sign-in so there may be skills that our scan couldn't access.
Here are examples from its store listing. Type one into your AI after you connect.
Yes. Some of its tools show an interactive widget in the chat, not only text. See more connectors with interactive UI.
This page updates every day. To ask about KAIROGEN from Claude, ChatGPT or a coding agent, connect the Agent Ready MCP server: it tracks ranks, tools and new listings across the AI plugin stores.