Cloudinary MCP Server
The Cloudinary MCP Server enables you to upload and manage media files on Cloudinary via Claude Desktop and compatible MCP clients.
Upload Media: Upload images, videos, and raw files using a file path, URL, or base64 data URI
Customization: Set custom public IDs, add tags for organization, and control overwrite options for existing assets
Large File Handling: Process large files in chunks with streaming responses for video uploads
URL Generation: Access uploaded assets via auto-generated HTTPS/HTTP URLs
Integration: Seamlessly integrates with Claude Desktop via MCP server configuration
Provides tools for uploading images and videos to Cloudinary through Claude Desktop and compatible MCP clients
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Cloudinary MCP Server upload this screenshot I just took and tag it as 'bug-report'"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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
Install Node.js (version 18 or higher) and npm from nodejs.org
Verify installation:
node --version npm --version
Install using npx (Recommended)
Navigate to the Claude configuration directory:
Windows:
C:\Users\NAME\AppData\Roaming\ClaudemacOS:
~/Library/Application Support/Claude/
You can also find these directories inside the Claude Desktop app: Claude Desktop > Settings > Developer > Edit Config
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"
}
}
}
}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:
Clone the repository:
git clone https://github.com/felores/cloudinary-mcp-server.git
cd cloudinary-mcp-serverInstall dependencies and build:
npm install
npm run buildRelated MCP server: Image Analysis MCP Server
Setup Instructions
First, ensure you have a Cloudinary account and get your credentials from the Cloudinary Console:
Cloud Name
API Key
API Secret
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.
Install dependencies and build the server:
npm install
npm run buildAvailable Tools
upload
Upload images and videos to Cloudinary.
Parameters:
file(required): Path to file, URL, or base64 data URI to uploadresource_type(optional): Type of resource ('image', 'video', or 'raw')public_id(optional): Custom public ID for the uploaded assetoverwrite(optional): Whether to overwrite existing assets with the same public IDtags(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"
}
});Available Tools
1 tooluploadB
Upload media (images/videos) to Cloudinary. For large files, the upload is processed in chunks and returns a streaming response. The uploaded asset will be available at:
HTTP: http://res.cloudinary.com/{cloud_name}/{resource_type}/upload/v1/{public_id}.{format}
HTTPS: https://res.cloudinary.com/{cloud_name}/{resource_type}/upload/v1/{public_id}.{format} where {cloud_name} is your Cloudinary cloud name, resource_type is 'image' or 'video', and format is determined by the file extension.
Inputs: file (required), resource_type, public_id, overwrite, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only one tool, there is no possibility for ambiguity or overlap between tools. The 'upload' tool has a clear, singular purpose of uploading media to Cloudinary, making it impossible for an agent to misselect among multiple options.
Since there is only one tool named 'upload', it inherently follows a consistent naming pattern. There are no other tools to compare against, so no inconsistencies can arise in verb style, case conventions, or other naming aspects.
A single tool is too few for a Cloudinary server, which typically handles a wide range of media operations like upload, delete, transform, list, and fetch. This minimal set severely limits functionality and will likely cause agent failures due to missing essential operations for the domain.
The tool set is severely incomplete for a Cloudinary media management server. It only provides upload functionality, with glaring gaps such as no delete, update, list, search, or transformation tools. This makes it impossible for agents to perform basic CRUD or lifecycle operations in the domain.
Maintenance
Related MCP Connectors
Upload, generate, organize, search, and transform images, videos, and files with AI-powered tools.
Upload, generate, organize, search, and transform images, videos, and files with AI-powered tools.
MCP server exposing the YourImageShare upload API (upload/list/delete) as tools for AI agents.
Manage Cloudinary upload presets, named transformations, mappings, triggers, and streaming profiles.
Related MCP Servers
- AlicenseAqualityDmaintenanceThis server generates placeholder image URLs from various providers, supporting input validation and integration with desktop applications like Claude and Cursor.112MIT
- AlicenseCqualityDmaintenanceA server that accepts image URLs and analyzes their content using GPT-4-turbo, enabling Claude AI assistants to understand and describe images through natural language.28MIT
- AlicenseNot gradedqualityDmaintenanceA lightweight MCP server for image processing and cloud uploads that automates resizing, converting, optimizing, and uploading images to services like AWS S3, Cloudflare R2, and Google Cloud Storage.25 npm18MIT
- AlicenseAqualityDmaintenanceMCP server for uploading images to ImgBB from Claude-compatible clients.3MIT