# Cloudinary Analysis MCP server

> Run AI image analysis such as moderation, captioning, tagging and object detection on images through Cloudinary's Analyze API.

- Listing: https://mcp.tc/i/cloudinary-analysis
- Connect: use the server's own URL `https://analysis.mcp.cloudinary.com/mcp` (OAuth sign-in at the server); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: OAuth sign-in
- Category: [AI & Machine Learning](https://mcp.tc/c/ai-ml)
- Vendor: Cloudinary
- Homepage: <https://cloudinary.com/documentation/cloudinary_llm_mcp>
- Docs: <https://cloudinary.com/documentation/cloudinary_llm_mcp>
- Repository: <https://github.com/cloudinary/analysis-mcp>
- Package: npm `@cloudinary/analysis-mcp`

## About

Connects to Cloudinary's Analyze API (Public Beta) so an assistant can analyze external images. Modes include AI Vision (general questions, yes/no moderation, custom tagging), captioning, Google tagging, logo and watermark detection, image quality, and content-aware detection models for fashion, text, human anatomy, COCO, LVIS and UniDet.

Runs as a hosted streamable HTTP endpoint, or locally with npx (Node.js 20.19.0 or later). The hosted server uses OAuth sign-in to a Cloudinary account, where you pick the product environment. API key authentication is not supported on the hosted Analysis server. Each analysis option needs an active subscription to the relevant Cloudinary add-on.

## What it can do

- Ask free-form questions about an image with AI Vision
- Moderate images with yes/no/unknown policy checks
- Tag images against your own tag names and descriptions
- Generate image captions
- Detect logos, watermarks, text, fashion items and objects
- Score image quality
- Check the status of an analysis task

## Tools (16)

- `analyze-ai-vision-general`: Answer open questions about an image: objects, scenes, text.
- `analyze-ai-vision-moderation`: Answer yes, no or unknown to policy and quality questions about an image.
- `analyze-ai-vision-tagging`: Tag an image using your own tag names and descriptions.
- `analyze-captioning`: Provide a caption for an image.
- `analyze-cld-fashion`: Detect clothing items and attributes like pockets, material and fastenings.
- `analyze-cld-text`: Detect whether an image contains text and where it is located.
- `analyze-coco`: Detect 80 common objects using the COCO model.
- `analyze-google-logo-detection`: Detect popular product logos in an image.
- `analyze-google-tagging`: Tag an image using Google's tagging service.
- `analyze-human-anatomy`: Identify parts of the human body in an image.
- `analyze-image-quality`: Run Cloudinary's image quality analysis model.
- `analyze-lvis`: Detect thousands of general object types using the LVIS model.
- `analyze-shop-classifier`: Tell whether an image is a studio product shot or a natural image.
- `analyze-unidet`: Detect diverse objects using the unified UniDet model.
- `analyze-watermark-detection`: Detect watermarks in an image.
- `tasks-get-status`: Get the status of an analysis task.

## Example prompts

- "Caption this image URL and list the objects in it."
- "Check whether this image contains a watermark or a visible logo."
- "Moderate this image: does it show people, text or branded products?"
- "Tag this product photo using my brand tags: studio shot, lifestyle, flat lay."

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

```bash
claude mcp add --transport http cloudinary-analysis https://analysis.mcp.cloudinary.com/mcp
```

2. Start Claude Code, type `/mcp`, pick **cloudinary-analysis** and choose **Authenticate**. A browser window opens for the Cloudinary sign-in.

Add `--scope user` to make it available in every project, not just this one.

### Claude Desktop

1. Open **Customize → Connectors**, click **+ Add**, then **Add custom connector**.

2. Name it **Cloudinary Analysis** and paste this URL:

```url
https://analysis.mcp.cloudinary.com/mcp
```

3. Click **Add**, then **Connect**, and sign in when Cloudinary asks.

Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

### claude.ai

1. Open the connector form on claude.ai. This button fills in the name and URL for you:

[Add to claude.ai](<https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=Cloudinary%20Analysis&connectorUrl=https%3A%2F%2Fanalysis.mcp.cloudinary.com%2Fmcp>) (opens connector settings)

2. Check that the URL reads `https://analysis.mcp.cloudinary.com/mcp` and click **Add**.

3. Click **Connect** and sign in when Cloudinary asks.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**.

### ChatGPT

1. On chatgpt.com, go to **Plugins**, select **+**, then **Add custom MCP server**.

2. Enter a name for the server.

3. Under **Connection**, paste `https://analysis.mcp.cloudinary.com/mcp` as the server URL, then for authentication choose **OAuth**. ChatGPT sends you to Cloudinary to sign in.

4. Check **I understand and want to continue**, then select **Create as a plugin**.

Whether you can add a custom MCP server depends on your ChatGPT plan and your workspace permissions (in Business workspaces, admins and owners can).

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=cloudinary-analysis&config=eyJ1cmwiOiJodHRwczovL2FuYWx5c2lzLm1jcC5jbG91ZGluYXJ5LmNvbS9tY3AifQ%3D%3D>) (opens Cursor)

Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):

`mcp.json`:

```json
{
  "mcpServers": {
    "cloudinary-analysis": {
      "url": "https://analysis.mcp.cloudinary.com/mcp"
    }
  }
}
```

Cursor shows **Needs authentication** next to the server. Click the button beside it to sign in.

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=cloudinary-analysis&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fanalysis.mcp.cloudinary.com%2Fmcp%22%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"cloudinary-analysis","type":"http","url":"https://analysis.mcp.cloudinary.com/mcp"}'
```

Or commit it to the repo in `.vscode/mcp.json`:

`.vscode/mcp.json`:

```json
{
  "servers": {
    "cloudinary-analysis": {
      "type": "http",
      "url": "https://analysis.mcp.cloudinary.com/mcp"
    }
  }
}
```

VS Code asks you to sign in the first time the server starts.

### Devin Desktop

1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):

`mcp_config.json`:

```json
{
  "mcpServers": {
    "cloudinary-analysis": {
      "serverUrl": "https://analysis.mcp.cloudinary.com/mcp"
    }
  }
}
```

2. Refresh the MCP server list in Cascade and sign in when asked.

Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers.

### Codex

```bash
codex mcp add cloudinary-analysis --url https://analysis.mcp.cloudinary.com/mcp
codex mcp login cloudinary-analysis
```

Or edit `~/.codex/config.toml` directly:

`config.toml`:

```toml
[mcp_servers.cloudinary-analysis]
url = "https://analysis.mcp.cloudinary.com/mcp"
```

### Gemini CLI

```bash
gemini mcp add --transport http cloudinary-analysis https://analysis.mcp.cloudinary.com/mcp
```

Then, inside Gemini CLI, run `/mcp auth cloudinary-analysis` to sign in.

This adds it to the current project. Add `-s user` to use it everywhere.

### Any client

Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file.

```json
{
  "mcpServers": {
    "cloudinary-analysis": {
      "type": "http",
      "url": "https://analysis.mcp.cloudinary.com/mcp"
    }
  }
}
```

Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE.

Client only starts local servers? Bridge it with `npx -y mcp-remote https://analysis.mcp.cloudinary.com/mcp`.

## Recent changes

- 2026-11-12 23:27 UTC: Tracking started: 16 tools read. Source: automatic check.

More on the History tab, with descriptions before and after for the newest entries: https://mcp.tc/i/cloudinary-analysis#history (Atom feed: https://mcp.tc/i/cloudinary-analysis/history.xml). It records what mcp.tc's anonymous checks saw, every 3 hours where the tool list can be read without sign-in; it is not a security review.

## Details

- Server version: 0.5.3
- Last checked: 2026-11-18 (reachable, asks for credentials)
- Listed: 2026-11-12
- Updated: 2026-11-12

---
Source: https://mcp.tc/i/cloudinary-analysis (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report
