Turn 
Claude into a creative engine
Connect Kolbo to Claude, OpenClaw, Hermes, NemoClaw and generate images, videos, music and more right from your conversations.
ClaudePaste one prompt — your AI sets it all up
Most agents can install Kolbo themselves. Copy this and paste it to Claude, ChatGPT, Cursor or any AI — it figures out the rest.
Connect the Kolbo AI MCP server (generate images, video, music and more).
- If you can run terminal commands (Claude Code, Cursor, Claude Desktop, or any local setup): run "npx -y @kolbo/mcp install" — it auto-configures Kolbo in the right place. If you can't run it, give me the command to run. Then I'll restart the app.
- If you're a browser chat (claude.ai, ChatGPT): add a custom connector with URL https://api.kolbo.ai/mcp under Settings → Connectors, then Connect → log in → Allow.
No API key needed — on first use a Kolbo login opens in my browser and I click Allow. When set up, confirm Kolbo is connected and offer to generate a test image of a sunset.Three steps to start
Runs on your machine for the full experience — generate, edit, and upload your own files. No API key to create. Pick your app:
Add Kolbo to Claude Desktop
Open Settings → Developer → Edit Config, paste this, then fully restart Claude Desktop:
Restart Claude Desktop
The Kolbo tools appear automatically once the app reloads.
Log in and create
The first time you use it, a Kolbo login opens in your browser — just click Allow. No API key to create. Then ask it to generate an image or upload one of your own files.
{
"mcpServers": {
"kolbo": {
"command": "npx",
"args": ["-y", "@kolbo/mcp@latest"]
}
}
}Live demo
Say it. Claude creates it.
Attach a product image, describe your campaign — Kolbo generates every asset automatically.
ClaudeOr connect instantly — right in the browser
Best for generating from text or URLs in claude.ai or ChatGPT — no setup. To upload your own files, use the full install above.
https://api.kolbo.ai/mcpSettings → Connectors → Add custom connector → paste → Connect → log in → Allow.
30 tools. One config block.
Everything your agent needs to create images, videos, music, audio, 3D and more.
Text to image
Flux, Seedream, DALL·E 3 and 7 more models — from a single prompt.
Image editing
Edit and transform existing images with a plain-language instruction.
Video generation
Kling, Seedance, Hailuo, Veo and more — text or image to video.
AI music
Full songs with lyrics, vocals and production from a description.
Text to speech
300+ natural voices, 30+ languages. Clone or browse the full library.
Sound effects
Custom sound effects and ambient audio from text.
AI chat
GPT-4o, Claude, Gemini — with web search and deep thinking.
3D models
Text or reference image to 3D with PBR texture support.
Transcription
Accurate transcripts from any audio or video file.
How it works
From API key to first generation in under two minutes.
Get your API key
Sign up at kolbo.ai (free), go to Settings → Developer, and create a new key.
Add Kolbo to your agent
Paste the config block into your agent's MCP settings. One copy-paste, then restart.
Start creating
Say "generate an image of…" or "make a 10s video" — your agent calls Kolbo automatically.
Built for agents that actually create.
Your agent picks the model.
Say "generate a video" — your agent reads the prompt and calls the right model. No flags, no extra parameters.
Everything lands in your media library.
Every image, video and audio generated through MCP syncs to your Kolbo library. Continue on the web or download originals.
Style DNA across every generation.
Reference your Visual DNA profiles and moodboards from any tool call. Consistent brand style, automatically applied.
Your agent just got a creative superpower.
One API key. One config block. 30 tools, 100+ models — available to every AI agent you use.