cloudinary-mcp-server

cloudinary-mcp-server avatar

by felores

Community Servers

MCP (Model Context Protocol) server for uploading media to Cloudinary using Claude Desktop

What is cloudinary-mcp-server

Cloudinary MCP Server

This MCP server provides tools for uploading images and videos to Cloudinary through Claude Desktop and compatible MCP clients.

Installation

Requirements: Node.js

  1. Install Node.js (version 18 or higher) and npm from nodejs.org
  2. Verify installation:
    node --version
    npm --version
    

Install using npx (Recommended)

  1. Navigate to the Claude configuration directory:

    • Windows: C:\Users\NAME\AppData\Roaming\Claude
    • macOS: ~/Library/Application Support/Claude/

    You can also find these directories inside the Claude Desktop app: Claude Desktop > Settings > Developer > Edit Config

  2. Add the following configuration to your MCP settings file:

{
  "mcpServers": {
    "cloudinary": {
      "command": "npx",
      "args": ["@felores/cloudinary-mcp-server@latest"],
      "env": {
        "CLOUDINARY_CLOUD_NAME": "your_cloud_name",
        "CLOUDINARY_API_KEY": "your_api_key",
        "CLOUDINARY_API_SECRET": "your_api_secret"
      }
    }
  }
}
  1. Make sure to replace the environment variables with your Cloudinary credentials from the Cloudinary Console.

Developer Installation

If you want to modify the server or contribute to development:

  1. Clone the repository:
git clone https://github.com/felores/cloudinary-mcp-server.git
cd cloudinary-mcp-server
  1. Install dependencies and build:
npm install
npm run build

Setup Instructions

  1. First, ensure you have a Cloudinary account and get your credentials from the Cloudinary Console:

    • Cloud Name
    • API Key
    • API Secret
  2. Add the server configuration to your Claude/Cline MCP settings file:

{
  "mcpServers": {
    "cloudinary": {
      "command": "node",
      "args": ["c:/path/to/cloudinary-mcp-server/dist/index.js"],
      "env": {
        "CLOUDINARY_CLOUD_NAME": "your_cloud_name",
        "CLOUDINARY_API_KEY": "your_api_key",
        "CLOUDINARY_API_SECRET": "your_api_secret"
      }
    }
  }
}

For Claude desktop app, edit the configuration file at the appropriate location for your OS.

  1. Install dependencies and build the server:
npm install
npm run build

Available Tools

upload

Upload images and videos to Cloudinary.

Parameters:

  • file (required): Path to file, URL, or base64 data URI to upload
  • resource_type (optional): Type of resource ('image', 'video', or 'raw')
  • public_id (optional): Custom public ID for the uploaded asset
  • overwrite (optional): Whether to overwrite existing assets with the same public ID
  • tags (optional): Array of tags to assign to the uploaded asset

Example usage in Claude/Cline:

use_mcp_tool({
  server_name: "cloudinary",
  tool_name: "upload",
  arguments: {
    file: "path/to/image.jpg",
    resource_type: "image",
    public_id: "my-custom-id"
  }
});

Leave a Comment

Comments section will be available soon. Stay tuned!

Frequently Asked Questions

What is MCP?

MCP (Model Context Protocol) is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications, providing a standardized way to connect AI models to different data sources and tools.

What are MCP Servers?

MCP Servers are lightweight programs that expose specific capabilities through the standardized Model Context Protocol. They act as bridges between LLMs like Claude and various data sources or services, allowing secure access to files, databases, APIs, and other resources.

How do MCP Servers work?

MCP Servers follow a client-server architecture where a host application (like Claude Desktop) connects to multiple servers. Each server provides specific functionality through standardized endpoints and protocols, enabling Claude to access data and perform actions through the standardized protocol.

Are MCP Servers secure?

Yes, MCP Servers are designed with security in mind. They run locally with explicit configuration and permissions, require user approval for actions, and include built-in security features to prevent unauthorized access and ensure data privacy.