Cloudinary MCP server

This MCP server integrates Cloudinary's capabilities with AI assistants, allowing them to upload and manage media assets in your Cloudinary cloud through the Model Context Protocol (MCP).

Installation and Setup

Prerequisites

• NodeJS
• MCP Client (like Claude Desktop App)
• Cloudinary API credentials from your Cloudinary console

Configuration for Claude Desktop

Add the Cloudinary MCP server to your Claude Desktop configuration by updating the claude_desktop_config.json file with the following:

{
    "mcpServers": {
        "cloudinary-mcp-server": {
            "command": "npx",
            "args": ["-y", "cloudinary-mcp-server"],
            "env": {
                "CLOUDINARY_CLOUD_NAME": "<cloud name>",
                "CLOUDINARY_API_KEY": "<api-key>",
                "CLOUDINARY_API_SECRET": "<api-secret>"
            }
        }
    }
}

Be sure to replace the placeholder values with your actual Cloudinary credentials:

• <cloud name> - Your Cloudinary cloud name
• <api-key> - Your Cloudinary API Key
• <api-secret> - Your Cloudinary API Secret

Available Tools

Upload Assets

Upload files (images, videos, or other assets) to your Cloudinary cloud:

Parameters:

• source: URL, file path, base64 content, or binary data to upload
• folder: (Optional) Folder path in Cloudinary
• publicId: (Optional) Custom public ID for the uploaded asset
• resourceType: Type of resource (image, video, raw, auto)
• tags: (Optional) Comma-separated list of tags to assign to the asset

Delete Assets

Remove assets from your Cloudinary cloud:

Parameters:

• publicId: The public ID of the asset to delete
• assetId: The asset ID of the asset to delete

Get Asset Details

Retrieve detailed information about a specific asset:

Parameters:

• assetId: The Cloudinary asset ID
• publicId: The public ID of the asset
• resourceType: Type of asset (image, raw, video)
• type: Delivery type (upload, private, authenticated, etc.)
• tags: Whether to include the list of tag names
• context: Whether to include contextual metadata
• metadata: Whether to include structured metadata

Find Assets

Search for assets in your Cloudinary cloud using query expressions:

Parameters:

• expression: Search expression (e.g., 'tags=cat' or 'public_id:folder/*')
• resourceType: Resource type (image, video, raw)
• maxResults: Maximum number of results (1-500)
• nextCursor: Next cursor for pagination
• tags: Include tags in the response
• context: Include context in the response

Get Usage Reports

Retrieve usage statistics for your Cloudinary account:

Parameters:

• date: (Optional) The date for the usage report in the format: yyyy-mm-dd. Must be within the last 3 months. Default: current date

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "cloudinary-mcp-server" '{"command":"npx","args":["-y","cloudinary-mcp-server"],"env":{"CLOUDINARY_CLOUD_NAME":"<cloud name>","CLOUDINARY_API_KEY":"<api-key>","CLOUDINARY_API_SECRET":"<api-secret>"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cloudinary-mcp-server": {
            "command": "npx",
            "args": [
                "-y",
                "cloudinary-mcp-server"
            ],
            "env": {
                "CLOUDINARY_CLOUD_NAME": "<cloud name>",
                "CLOUDINARY_API_KEY": "<api-key>",
                "CLOUDINARY_API_SECRET": "<api-secret>"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "cloudinary-mcp-server": {
            "command": "npx",
            "args": [
                "-y",
                "cloudinary-mcp-server"
            ],
            "env": {
                "CLOUDINARY_CLOUD_NAME": "<cloud name>",
                "CLOUDINARY_API_KEY": "<api-key>",
                "CLOUDINARY_API_SECRET": "<api-secret>"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect