Cloudinary Asset Management

Cloudinary Asset Management MCP Server

Summary

Table of Contents

• Cloudinary Asset Management MCP Server
• Installation
• Configuration
• Authentication
• Available Tools
• Custom Tools
• Progressive Discovery
• Development
• Building from Source
• Contributions

Installation

The MCP server requires Node.js 20.19.0 or later.

Claude Desktop

Install the MCP server as a Desktop Extension using the pre-built mcp-server.mcpb file:

Simply drag and drop the mcp-server.mcpb file onto Claude Desktop to install the extension.

The MCP bundle package includes the MCP server and all necessary configuration. Once installed, the server will be available without additional setup.

[!NOTE]

MCP bundles provide a streamlined way to package and distribute MCP servers. Learn more about Desktop Extensions.

Cursor

Or manually:

1. Open Cursor Settings
2. Select Tools and Integrations
3. Select New MCP Server
4. If the configuration file is empty paste the following JSON into the MCP Server Configuration:

{

"command": "npx", "args": [ "@cloudinary/asset-management-mcp", "start", "--api-key", "", "--api-secret", "", "--cloud-name", "" ] }

Claude Code CLI

claude mcp add CloudinaryAssetMgmt -- npx -y @cloudinary/asset-management-mcp start --api-key  --api-secret  --cloud-name 

Gemini

gemini mcp add CloudinaryAssetMgmt -- npx -y @cloudinary/asset-management-mcp start --api-key  --api-secret  --cloud-name 

Windsurf

Refer to Official Windsurf documentation for latest information

1. Open Windsurf Settings
2. Select Cascade on left side menu
3. Click on Manage MCPs. (To Manage MCPs you should be signed in with a Windsurf Account)
4. Click on View raw config to open up the mcp configuration file.
5. If the configuration file is empty paste the full json

{

"command": "npx", "args": [ "@cloudinary/asset-management-mcp", "start", "--api-key", "", "--api-secret", "", "--cloud-name", "" ] }

</details>

VS Code

Or manually:

Refer to Official VS Code documentation for latest information

1. Open Command Palette
2. Search and open MCP: Open User Configuration. This should open mcp.json file
3. If the configuration file is empty paste the full json

{

"command": "npx", "args": [ "@cloudinary/asset-management-mcp", "start", "--api-key", "", "--api-secret", "", "--cloud-name", "" ] }

Stdio installation via npm To start the MCP server, run:

npx @cloudinary/asset-management-mcp start --api-key  --api-secret  --cloud-name 

For a full list of server arguments, run:

npx @cloudinary/asset-management-mcp --help

Configuration

Environment Variables

The MCP server supports the following environment variables:

CLOUDINARY_URL Format

You can use a single CLOUDINARY_URL instead of individual variables:

CLOUDINARY_URL=cloudinary://API_KEY:API_SECRET@CLOUD_NAME

Response Header Collection

You can configure the server to include Cloudinary API response headers (such as x-request-id and rate limit info) in tool output. This is useful for debugging and monitoring.

Set CLOUDINARY_COLLECT_HEADERS to control which headers are collected:

# Collect all response headers

CLOUDINARY_COLLECT_HEADERS=true

Collect specific headers by exact name (comma-separated)

CLOUDINARY_COLLECT_HEADERS=x-request-id,x-featureratelimit-limit,x-featureratelimit-remaining

Mix exact names, prefix matching, and regex matching

CLOUDINARY_COLLECT_HEADERS=x-request-id,prefix:x-featureratelimit-

Header matching specs

Each entry in the comma-separated list is matched against response header names:

You can also set this via the CLOUDINARY_URL query parameter:

CLOUDINARY_URL=cloudinary://API_KEY:API_SECRET@CLOUD_NAME?collect_headers=true

When enabled, collected headers appear in an _headers field in the tool response. When not set, no headers are collected and responses are unchanged.

MCP Apps

The server can expose interactive MCP UI Apps (spec-aligned with io.modelcontextprotocol/ui) that hosts can render alongside tool results — for example, an asset gallery for list results, a single-asset detail view, and an upload UI.

Apps are enabled by default. Use the --mcp-apps flag (available on both start and serve) or the CLOUDINARY_MCP_APPS environment variable to override this behaviour:

Available app names: asset-gallery, asset-details, asset-upload.

# Disable all apps

npx @cloudinary/asset-management-mcp serve --mcp-apps none

Enable only the gallery

npx @cloudinary/asset-management-mcp start --mcp-apps asset-gallery

Disable via env var

CLOUDINARY_MCP_APPS=none npx @cloudinary/asset-management-mcp start

Precedence: CLI flag > environment variable > built-in default.

Authentication

The MCP server uses your Cloudinary API key and secret for authentication:

{

"env": { "CLOUDINARY_CLOUD_NAME": "demo", "CLOUDINARY_API_KEY": "123456789012345", "CLOUDINARY_API_SECRET": "abcdefghijklmnopqrstuvwxyz12" } }

Available Tools

The MCP server exposes Cloudinary's Asset Management API as tools. Use your AI application to discover and invoke the available tools for uploading, managing, searching, and transforming your media assets.

Usage Examples

Example 1: Upload and Transform an Image

1. Upload a local image: "Upload file:///Users/me/photo.jpg to Cloudinary as 'hero-image'"

1. Transform it: "Transform asset 'hero-image' with transformations 'c_fill,w_800,h_600/e_sharpen'"
2. Get details: "Show me details for asset with ID [asset-id]"

Example 2: Search and Organize Assets

1. Search for images: "Find all images with tag 'product' uploaded in the last 7 days"

1. Create folder: "Create a new folder called 'summer-2024-products'"
2. List assets: "Show me all video assets in the 'marketing' folder"

Example 3: Generate Archive

1. Get transformation docs: "Show me the Cloudinary transformation reference"

1. Apply transformations: "Transform 'banner' asset with 'c_scale,w_1200/f_auto,q_auto'"
2. Create archive: "Generate a ZIP archive of all images with tag 'export-ready'"

Example 4: Asset Management Workflow

1. Upload multiple files: "Upload all images from folder /assets/new-products/"

1. Add tags: "Update asset [asset-id] and add tags 'featured,homepage'"
2. Get usage stats: "Show my Cloudinary account usage statistics"

Custom Tools

This MCP server includes two powerful custom tools:

get-tx-reference

Retrieves the complete Cloudinary transformation reference documentation.

When to use:

• Before creating or modifying transformations
• When user asks about image/video effects, resizing, cropping, filters

Example:

Use get-tx-reference to learn about available transformations

transform-asset

Applies transformations to existing assets using Cloudinary's explicit API.

Parameters:

• publicId - The asset's public ID
• transformations - Transformation string (e.g., c_fill,w_300,h_200)
• resourceType - Type: image, video, or raw (default: image)
• invalidate - Invalidate CDN cache (default: false)

Example:

Transform asset "sample" with transformations "c_fill,w_500,h_500/e_sepia"

Progressive Discovery

MCP servers with many tools can bloat LLM context windows, leading to increased token usage and tool confusion. Dynamic mode solves this by exposing only a small set of meta-tools that let agents progressively discover and invoke tools on demand.

To enable dynamic mode, pass the --mode dynamic flag when starting your server:

{

"mcpServers": { "CloudinaryAssetMgmt": { "command": "npx", "args": ["@cloudinary/asset-management-mcp", "start", "--mode", "dynamic"], // ... other server arguments } } }

In dynamic mode, the server registers only the following meta-tools instead of every individual tool:

• `list_tools`: Lists all available tools with their names and descriptions.
• `describe_tool_input`: Returns the input schema for one or more tools by name.
• `execute_tool`: Executes a tool by name with its arguments.
• `list_scopes`: Lists the scopes available on the server.

This approach significantly reduces the number of tokens sent to the LLM on each request, which is especially useful for servers with a large number of tools.

You can combine dynamic mode with scope and tool filters:

{

"mcpServers": { "CloudinaryAssetMgmt": {