Cloudinary Analysis MCP Server

Summary

Analyze API (Beta): Use the Analyze API to analyze any external asset and return details based on the type of analysis requested.

Currently supports the following analysis options:

• AI Vision - Tagging

• AI Vision - Moderation

• AI Vision - General

• Captioning

• Cld Fashion

• Cld Text

• Coco

• Google Tagging

• Human Anatomy

• Image Quality Analysis

• Lvis

• Shop Classifier

• Unidet

• Watermark Detection

Notes:

• The Analyze API is currently in development and is available as a Public Beta, which means we value your feedback, so please feel free to share any thoughts with us.

• The analysis options require an active subscription to the relevant add-on. Learn more about registering for add-ons.

The API supports both Basic Authentication using your Cloudinary API Key and API Secret (which can be found on the Dashboard page of your Cloudinary Console) or OAuth2 (Contact support for more information regarding OAuth).

Related MCP server: @audiolabtools/mcp-server

Table of Contents

• Cloudinary Analysis MCP Server

  • Installation

  • Progressive Discovery

  • Configuration

  • Authentication

• Development

  • Building from Source

  • Contributions

Installation

The MCP server requires Node.js 20.19.0 or later.

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.

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/analysis-mcp",
    "start",
    "--cloud-name",
    "CLOUD_NAME",
    "--api-key",
    "",
    "--api-secret",
    "",
    "--o-auth2",
    ""
  ]
}

claude mcp add CloudinaryAnalysis -- npx -y @cloudinary/analysis-mcp start --cloud-name CLOUD_NAME --api-key  --api-secret  --o-auth2 

gemini mcp add CloudinaryAnalysis -- npx -y @cloudinary/analysis-mcp start --cloud-name CLOUD_NAME --api-key  --api-secret  --o-auth2 

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/analysis-mcp",
    "start",
    "--cloud-name",
    "CLOUD_NAME",
    "--api-key",
    "",
    "--api-secret",
    "",
    "--o-auth2",
    ""
  ]
}

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/analysis-mcp",
    "start",
    "--cloud-name",
    "CLOUD_NAME",
    "--api-key",
    "",
    "--api-secret",
    "",
    "--o-auth2",
    ""
  ]
}

npx @cloudinary/analysis-mcp start --cloud-name CLOUD_NAME --api-key  --api-secret  --o-auth2 

For a full list of server arguments, run:

npx @cloudinary/analysis-mcp --help

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": {
    "CloudinaryAnalysis": {
      "command": "npx",
      "args": ["@cloudinary/analysis-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.

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.

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

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"
  }
}

Development

Building from Source

Prerequisites

• Node.js v20 or higher

• npm, pnpm, bun, or yarn

Build Steps

# Clone the repository
git clone https://github.com/cloudinary/analysis-mcp.git
cd analysis-mcp

# Install dependencies
npm install

# Build the project
npm run build

# Run locally
npm start

Contributions

While we value contributions to this MCP Server, the code is generated programmatically from the Cloudinary API spec. Any manual changes to generated files will be overwritten on the next generation.

We look forward to hearing your feedback. Feel free to open a PR or issue with a proof of concept and we'll do our best to include it in a future release.

MCP Server Created by Speakeasy