
Avocado AI Now Works Inside Claude, Cursor, and Any MCP Client
You can now generate images, videos, music, and voiceovers directly inside Claude. No tab-switching. No copy-pasting prompts between tools. Describe what you want, get the asset, keep working.
We just shipped our MCP server to the official MCP Registry and Smithery with a perfect 100/100 quality score. Here's what that means for creators and brands, and how to set it up in under 2 minutes.
Launch video
What is MCP (and why should you care)?
MCP stands for Model Context Protocol. It lets AI assistants like Claude, Cursor, Windsurf, and others connect to external tools. Think of it like installing an app on your phone, but for your AI assistant.
Before MCP: you chat with Claude, get ideas, then switch to another tool to create the actual assets.
After MCP: you stay in Claude. Ask for a product photo. It appears. Ask for a video ad. It renders. Ask for background music. Done. Everything lands in your Avocado AI workspace, ready to download or keep editing.
What You Can Create
Six tools, three guided workflows, 19+ AI models. All accessible through natural conversation.
Images with models like Flux Pro Ultra, Google Imagen 4, Ideogram V3 (best for text in images), Recraft V4 Pro, GPT Image 1.5, Grok Imagine, and more. Just describe what you want. Costs 1-2 credits per image depending on the model.
Videos powered by Seedance 2.0 from ByteDance. Describe a scene and get a high-quality AI video in 2-5 minutes. Videos render in 720p or 1080p and land in your workspace when ready.
Music powered by ElevenLabs. Describe the genre, mood, tempo, and instruments. Get original tracks from 30 seconds to 5 minutes. Perfect for ad backgrounds, content intros, or social media audio.