# Cloudinary Analysis

The Cloudinary Analysis MCP server for Claude Code sends external images to Cloudinary for analysis. It can check moderation, produce captions and tags, and run other supported analysis modes.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: cloudinary
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/cloudinary/analysis-mcp
- Updated: 2026-11-12
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/cloudinary-analysis

## What it does

Cloudinary Analysis sends an external asset to the Analyze API and returns results for the requested analysis. Available modes include moderation, general AI Vision queries, captioning, tagging, image quality checks, and watermark detection. Models also cover specific categories such as fashion and human anatomy.

The Analyze API is in public beta. Each analysis mode requires an active subscription to its corresponding Cloudinary add-on. Authentication uses a Cloudinary API Key and API Secret, or OAuth2.

## Requirements
- Needs: Node.js (commands run via npx)
- Remote server: `https://analysis.mcp.cloudinary.com/mcp`
- Environment variables: `CLOUDINARY_CLOUD_NAME`, `CLOUDINARY_API_KEY`, `CLOUDINARY_API_SECRET` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

1. **Platform CLI: remote server**
```bash
claude mcp add --transport http analysis-mcp https://analysis.mcp.cloudinary.com/mcp
```

2. **Platform CLI**
```bash
claude mcp add --env CLOUDINARY_CLOUD_NAME=<CLOUDINARY_CLOUD_NAME> --env CLOUDINARY_API_KEY=<CLOUDINARY_API_KEY> --env CLOUDINARY_API_SECRET=<CLOUDINARY_API_SECRET> --transport stdio cloudinary-analysis -- npx -y @cloudinary/analysis-mcp
```
Replace <…> with your own values

### Codex

1. **Platform CLI: remote server**
```bash
codex mcp add cloudinary-analysis --url https://analysis.mcp.cloudinary.com/mcp
```

2. **Platform CLI**
```bash
codex mcp add cloudinary-analysis --env CLOUDINARY_CLOUD_NAME=<CLOUDINARY_CLOUD_NAME> --env CLOUDINARY_API_KEY=<CLOUDINARY_API_KEY> --env CLOUDINARY_API_SECRET=<CLOUDINARY_API_SECRET> -- npx -y @cloudinary/analysis-mcp
```
Replace <…> with your own values

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "cloudinary-analysis": {
            "url": "https://analysis.mcp.cloudinary.com/mcp"
        }
    }
}
```
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "cloudinary-analysis": {
            "command": "npx",
            "args": [
                "-y",
                "@cloudinary/analysis-mcp"
            ],
            "env": {
                "CLOUDINARY_CLOUD_NAME": "<CLOUDINARY_CLOUD_NAME>",
                "CLOUDINARY_API_KEY": "<CLOUDINARY_API_KEY>",
                "CLOUDINARY_API_SECRET": "<CLOUDINARY_API_SECRET>"
            }
        }
    }
}
```
Replace <…> with your own values

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "cloudinary-analysis": {
            "type": "http",
            "url": "https://analysis.mcp.cloudinary.com/mcp"
        }
    }
}
```
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "cloudinary-analysis": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "@cloudinary/analysis-mcp"
            ],
            "env": {
                "CLOUDINARY_CLOUD_NAME": "<CLOUDINARY_CLOUD_NAME>",
                "CLOUDINARY_API_KEY": "<CLOUDINARY_API_KEY>",
                "CLOUDINARY_API_SECRET": "<CLOUDINARY_API_SECRET>"
            }
        }
    }
}
```
Replace <…> with your own values

### Gemini CLI

1. **Platform CLI: remote server**
```bash
gemini mcp add -t http cloudinary-analysis https://analysis.mcp.cloudinary.com/mcp
```

2. **Platform CLI**
```bash
gemini mcp add -e CLOUDINARY_CLOUD_NAME=<CLOUDINARY_CLOUD_NAME> -e CLOUDINARY_API_KEY=<CLOUDINARY_API_KEY> -e CLOUDINARY_API_SECRET=<CLOUDINARY_API_SECRET> cloudinary-analysis npx -y @cloudinary/analysis-mcp
```
Replace <…> with your own values

## When to use it
- check an image for policy violations
- generate a caption or tags for an image
- assess image quality
- detect a watermark in an image

## Example prompts
- Check this external image for moderation issues with Cloudinary.
- Generate a caption and tags for this image using Cloudinary.
- Assess this image’s quality through Cloudinary.

## Similar
- [cloudinary-docs](https://affpapa.org/en/nevibecode/skills/cloudinary-docs.md) — skill · 1100 installs
- [cloudinary-transformations](https://affpapa.org/en/nevibecode/skills/cloudinary-transformations.md) — skill · 906 installs
- [SEO Web Analysis MCP — Site Audit & Tech Stack](https://affpapa.org/en/nevibecode/mcp/seo-web-analysis-mcp-site-audit-tech-stack.md) — MCP server · 9357 installs
- [Token Holder Analysis — Distribution & Whale Detection](https://affpapa.org/en/nevibecode/mcp/token-holder-analysis-distribution-whale-detection.md) — MCP server · 5218 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
