Avocado AI
About
Collaborative AI creative workspace for agencies and ecommerce teams to generate on-brand images, videos, and ad creative at scale.
Details
- Author
- Unknown
- Categories
- Productivity, Communication
Jump to
Avocado AI Now Has an MCP Server: Generate Images, Videos, Music, and Speech From Any AI Assistant
Avocado AI now has an MCP server. Generate images, videos, music, and voiceovers from Claude, Cursor, or any MCP client, without leaving your chat. Everything saves straight to your workspace.
We just shipped something we're excited about: an MCP (Model Context Protocol) server that lets you use Avocado AI's full creative toolkit directly from Claude, Cursor, Windsurf, or any MCP-compatible client.
No browser tab. No copy-pasting prompts. Just tell your AI assistant what you want to create, and it happens.
MCP is an open standard created by Anthropic that lets AI assistants connect to external tools and services. Think of it as USB-C for AI: one universal way for any AI client to talk to any tool provider.
When you connect Avocado AI's MCP server to your AI assistant, it gains the ability to generate images, videos, music, and speech on your behalf. Everything saves automatically to your Avocado AI workspace.
The Avocado AI MCP server exposes 6 tools.
Access 19+ state-of-the-art image models from a single tool:
- Flux Pro Ultra: high-quality professional images with ultra detail
- Imagen 4 and Imagen 4 Ultra: Google's photorealistic image models
- Ideogram V3: best-in-class text rendering, great for logos and typography
- Recraft V4 Pro: design-focused generation with style control
- SeedDream V5: ByteDance's latest image model
- GPT Image 1.5: OpenAI's image generation
- Grok Imagine: xAI's image model
- And 12 more
You can control aspect ratio (1:1, 16:9, 9:16, 4:3, 3:4, 21:9, 3:2, 2:3) and generate up to 4 images at once. Most models cost 1 credit per image; premium models cost 2.
Create AI videos using ByteDance's Seedance 2.0. Describe the motion, camera angles, and scene details, and get a high-quality video back.
- Duration: 5 to 15 seconds
- Resolution: 720p or 1080p
- Fast mode: quicker results at slightly lower quality
- Cost: ~4 credits/sec at 720p, ~9 credits/sec at 1080p
Videos take 2 to 5 minutes to generate and appear in your workspace automatically.
Create original music tracks from text descriptions, powered by ElevenLabs. Describe the genre, mood, tempo, and instruments you want.
- Duration: 30 seconds to 5 minutes
- Cost: 4 credits per 30-second block
Tracks save directly to your Avocado AI library.
Convert text to natural-sounding speech with 9 voice options, powered by ElevenLabs:
- Max length: 40,000 characters
- Cost: 3 credits per 1,000 characters
Check your current credit balance, membership tier, and estimated remaining generations without leaving your AI assistant.
Browse all available image generation models with descriptions and credit costs. This tool is free and doesn't require authentication, so you can explore what's available before signing up.
Go to yourAPI Keys pageand create a key
Your key will look like avk_xxxxxxxxxxxx
Add this to your Claude Desktop MCP config (claude_desktop_config.json):
{
"mcpServers": {
"avocado-ai": {
"url": "https://www.avocadoai.co/api/mcp",
"headers": {
"Authorization": "Bearer avk_your_api_key_here"
}
}
}
}
claude mcp add --transport http avocado-aihttps://www.avocadoai.co/api/mcp--header "Authorization: Bearer avk_your_api_key_here"
Point your client to the endpoint URL and pass your API key as a Bearer token in the Authorization header. The server uses the standard Streamable HTTP transport, so any MCP client that supports it will work.
Here are some things you can do once connected.
"Generate a hero image for my landing page"Your AI assistant calls generate_image with your description, picks the best model, and the image appears in your Avocado AI workspace ready to download.
"Create a 10-second product demo video"Calls generate_video with Seedance 2.0. The video renders in the background and shows up in your workspace in a few minutes.
"Make a 60-second lo-fi beat for my YouTube video"Calls generate_music with your description. A finished track appears in your library.
"Read this blog post aloud in a deep male voice"Calls text_to_speech with the Adam voice. An MP3 saves to your workspace.
"How many credits do I have left?"Calls check_credits and tells you your balance, tier, and how many more generations you can run.
For developers who want to know what's under the hood:
- Protocol: MCP over Streamable HTTP (POST/GET)
- SDK: @modelcontextprotocol/sdk v1.29+
- Auth: Bearer token via Authorization header, with query parameter fallback (?apiKey=avk_...) for gateway compatibility
- No OAuth flow: auth errors return MCP-level error messages instead of HTTP 401, preventing unwanted OAuth redirects in MCP clients
- CORS: fully enabled for cross-origin access
- Timeout: 120 seconds per request
- Generated content: all images, videos, music, and audio are stored in your Avocado AI workspace and accessible from the web app
The MCP uses the same credit system as the Avocado AI web app.
Create an API key atavocadoai.co/api-keys
Connect to your favorite AI assistant using the config above
Everything you generate through the MCP shows up in yourAvocado AI workspace, the same place your web app generations live. One account, one library, accessible from anywhere.
Avocado AI is a collaborative creative AI platform with 19+ image models, video generation, music creation, and text-to-speech, all in one place.Try it free.
Remote MCP server for MindMeister. Create, edit, and organize mind maps from your AI assistant. Hosted (streamable-HTTP) — connect at https://mcp.mindmeister.com/mcp
Collaborative word processor you can use with your agent
Keep teams & agents coordinated automatically
Carryo is a remote MCP server for sharing Claude or ChatGPT-created HTML artifacts as live links.
An MCP server for integrating ClickUp tasks with AI applications, featuring task dependency management and bug fixes.
The Collaboard MCP Server lets AI assistants create, search, analyze, and transform whiteboards into visual, collaborative workspaces.
An MCP server that enables AI assistants to interact with Confluence content through a standardized interface.
Publish Markdown or HTML to a clean, shareable link straight from your AI assistant — OAuth, no API keys.
An MCP server for interacting with the esa.io knowledge-sharing platform.
Access the esa.io API to manage your team's knowledge base.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.



