Skip to main content

Cloudinary Asset Management Extension

This tutorial covers how to add the Cloudinary Asset Management MCP Server as a Goose extension to automate complex image processing workflows that would typically require specialized design software or manual editing.

TLDR

Launch the installer

Environment Variable

CLOUDINARY_URL: cloudinary://<your_api_key>:<your_api_secret>@<your_cloud_name>

Configuration​

info

Note that you'll need Node.js installed on your system to run this command, as it uses npx. You'll also need a Cloudinary account.

  1. Launch the installer
  2. Press Yes to confirm the installation
  3. Obtain your CLOUDINARY_URL from your Cloudinary dashboard and paste it in
  4. Click Save Configuration
  5. Scroll to the top and click Exit from the upper left corner

Example Usage​

Let's use the Cloudinary extension to find and transform product images with advanced visual effects. In this example, we'll demonstrate how Goose can help you:

  1. Search for specific images in your media library
  2. Apply complex transformations including background removal
  3. Add text overlays with precise positioning
LLM

Anthropic's Claude 4 Sonnet was used for this task.

Goose Prompt​

1. find shoe images in my Cloudinary samples that have 'shoe' in the filename or public ID.
2. Let's transform the first result and only extract just the shoes
3. Add a white text overlay that says I love shoes. Make sure it's above the shoes
4. Add a background to the image. It should be black

Goose Output​

I'll help you find shoe images in your Cloudinary samples and apply the transformations you've requested. Let me start by searching for images with 'shoe' in the filename or public ID.

─── list-images | cloudinaryassetmanagement ──────────────────────────
maxResults: 50
prefix: samples
type: upload

Perfect! I found the shoe images in your Cloudinary samples. I can see:

1. **`samples/shoe`** - A single shoe image (publicId: `samples/shoe`)
2. **`samples/ecommerce/shoes`** - A pair of shoes (publicId: `samples/ecommerce/shoes`)

Let me use the first result (`samples/shoe`) as requested and apply all the transformations you want:

1. Extract just the shoes (using background removal)
2. Add white text overlay "I love shoes" above the shoes
3. Add a black background

Here's the transformed image URL with all your requested modifications:

https://res.cloudinary.com/dd8qwbjtv/image/upload/e_background_removal/b_black/l_text:Arial_60:I%20love%20shoes,co_white,g_north,y_50/samples/shoe

Let me break down what each transformation does:

- `e_background_removal` - Removes the background and extracts just the shoe
- `b_black` - Adds a black background to replace the removed background
- `l_text:Arial_60:I%20love%20shoes,co_white,g_north,y_50` - Adds white text overlay:
  - `Arial_60` - Arial font, size 60
  - `I%20love%20shoes` - The text (URL encoded)
  - `co_white` - White color
  - `g_north` - Positioned at the top (north)
  - `y_50` - 50 pixels offset from the top

Here are the images we found with "shoe" in the filename/public ID:

1. **First result (used for transformation)**: `samples/shoe`
   - Original: https://res.cloudinary.com/dd8qwbjtv/image/upload/v1708364167/samples/shoe.jpg
   - **Transformed**: https://res.cloudinary.com/dd8qwbjtv/image/upload/e_background_removal/b_black/l_text:Arial_60:I%20love%20shoes,co_white,g_north,y_50/samples/shoe

2. **Second result**: `samples/ecommerce/shoes`
   - Original: https://res.cloudinary.com/dd8qwbjtv/image/upload/v1708364144/samples/ecommerce/shoes.png

The transformed image now has:
✅ Just the shoes extracted (background removed)
✅ White text "I love shoes" positioned above the shoes
✅ Black background applied

You can click on the transformed URL to see the final result!