@cloudinary/analysis-mcp MCP Server

Endpoints

Endpoint	Method	Description
/mcp	POST	Streamable HTTP transportRecommended
/sse	GET	SSE transportDeprecated

Server URL

http://analysis.mcp.cloudinary.com/mcp

Configuration

Add this to your MCP client configuration. OAuth is used by default when no headers are provided.

Minimal (OAuth)

{
  "mcpServers": {
    "@cloudinary/analysis-mcp": {
      "url": "http://analysis.mcp.cloudinary.com/mcp"
    }
  }
}

With API Key

{
  "mcpServers": {
    "@cloudinary/analysis-mcp": {
      "url": "http://analysis.mcp.cloudinary.com/mcp",
      "headers": {
        "cloudinary-url": "cloudinary://api_key:api_secret@cloud_name"
      }
    }
  }
}

Authentication

Method	Description
OAuth 2.0	Default. The OAuth flow is initiated automatically when the client connects with no auth headers.
API Key	Pass `cloudinary-url` header, or individual `cloudinary-cloud-name`, `cloudinary-api-key`, `cloudinary-api-secret` headers.

Configuration Headers

Optional headers to customize server behavior. Applied at session creation time.

Header	Description
`cloudinary-region`	API region: `api`, `api-eu`, or `api-ap`
`cloudinary-tools`	Comma-separated list of tools to enable (e.g. `search-assets,list-images`)

Response Headers

API response headers are collected into _meta.headers on each tool result. The debug preset is active by default.

Header	Description
`cloudinary-collect-headers`	Control which response headers are returned. Accepts: `debug` — rate-limit + request ID (default) `ratelimit` — rate-limit headers only `all` — every response header Or a comma-separated list of exact names, `prefix:<value>`, `regex:<pattern>`, and preset names
`cloudinary-embed-headers`	Set to `true` to also include collected headers in the response body as `_headers`, for clients that don't surface `_meta`

Tool result structure

{
  "_meta": {
    "headers": {
      "x-featureratelimit-limit": "5000",
      "x-featureratelimit-remaining": "4998",
      "x-featureratelimit-reset": "Thu, 13 Feb 2026 00:00:00 GMT",
      "x-request-id": "bfeaccc60050594832508590a358a1a4"
    }
  },
  "content": [{ "type": "text", "text": "{...}" }]
}

Available Tools (16)

analyze-ai-vision-general analyze-ai-vision-moderation analyze-ai-vision-tagging analyze-captioning analyze-cld-fashion analyze-cld-text analyze-coco analyze-google-logo-detection analyze-google-tagging analyze-human-anatomy analyze-image-quality analyze-lvis analyze-shop-classifier analyze-unidet analyze-watermark-detection tasks-get-status

destructiveidempotentopenWorldreadOnly

Analyze - AI Vision General

The General mode serves a wide array of applications by providing detailed answers to diverse questions about an image. Users can inquire about any aspect of an image, such as identifying objects, understanding scenes, or interpreting text within the image.

Parameter	Type	Description
`request` required	{ }object	A JSON object containing request parameters
`async`	◉boolean	Whether to perform the analysis asynchronously. If true, the response is returned immediately and analysis is done in the background. Once complete, a webhook notification will be sent to the specified URL and/or to the URLs defined in the Webhook Notifications settings of your Cloudinary Console.
`notification_url`	Abcstring	The webhook URL to notify when the analysis is complete. Only relevant when async is set to true.
`prompts`	[ ]array	One or more prompts of open questions or tasks with an open answer
`source` required	{ }object

destructiveidempotentopenWorldreadOnly

Analyze - AI Vision Moderation

The Moderation mode accepts multiple questions about an image, to which the response provides concise answers of "yes," "no," or "unknown." This functionality allows for a nuanced evaluation of whether the image adheres to specific content policies, creative specs, or aesthetic criteria.

Parameter	Type	Description
`request` required	{ }object	A JSON object containing request parameters
`async`	◉boolean	Whether to perform the analysis asynchronously. If true, the response is returned immediately and analysis is done in the background. Once complete, a webhook notification will be sent to the specified URL and/or to the URLs defined in the Webhook Notifications settings of your Cloudinary Console.
`notification_url`	Abcstring	The webhook URL to notify when the analysis is complete. Only relevant when async is set to true.
`rejection_questions`	[ ]array	A list of yes/no questions
`source` required	{ }object

destructiveidempotentopenWorldreadOnly

Analyze - AI Vision Tagging

The Tagging mode accepts a list of tag names along with their corresponding descriptions. If the image matches the description, which may encompass various elements, it will be appropriately tagged. This approach enables customers to align with their own brand taxonomy, offering a dynamic, flexible, and open method for image classification.

Parameter	Type	Description
`request` required	{ }object	A JSON object containing request parameters
`async`	◉boolean	Whether to perform the analysis asynchronously. If true, the response is returned immediately and analysis is done in the background. Once complete, a webhook notification will be sent to the specified URL and/or to the URLs defined in the Webhook Notifications settings of your Cloudinary Console.
`notification_url`	Abcstring	The webhook URL to notify when the analysis is complete. Only relevant when async is set to true.
`source` required	{ }object
`tag_definitions` required	[ ]array

destructiveidempotentopenWorldreadOnly

Analyze - Captioning

Provides a caption for an image.

Parameter	Type	Description
`request` required	{ }object	A JSON object containing request parameters
`async`	◉boolean	Whether to perform the analysis asynchronously. If true, the response is returned immediately and analysis is done in the background. Once complete, a webhook notification will be sent to the specified URL and/or to the URLs defined in the Webhook Notifications settings of your Cloudinary Console.
`notification_url`	Abcstring	The webhook URL to notify when the analysis is complete. Only relevant when async is set to true.
`source` required	{ }object

destructiveidempotentopenWorldreadOnly

Analyze - Cld-Fashion

Analyze an image using the [Cld-Fashion](https://cloudinary.com/documentation/cloudinary_ai_content_analysis_addon#ai_based_image_captioning) content-aware detection model. Cloudinary's fashion model is specifically dedicated to items of clothing. The response includes attributes of the clothing identified, for example whether the garment contains pockets, its material and the fastenings used.

Parameter	Type	Description
`request` required	{ }object	A JSON object containing request parameters
`async`	◉boolean	Whether to perform the analysis asynchronously. If true, the response is returned immediately and analysis is done in the background. Once complete, a webhook notification will be sent to the specified URL and/or to the URLs defined in the Webhook Notifications settings of your Cloudinary Console.
`notification_url`	Abcstring	The webhook URL to notify when the analysis is complete. Only relevant when async is set to true.
`source` required	{ }object

destructiveidempotentopenWorldreadOnly

Analyze - Cld-Text

Analyze an image using the [Cld-Text](https://cloudinary.com/documentation/cloudinary_ai_content_analysis_addon#ai_based_image_captioning) content-aware detection model. Cloudinary's text model tells you if your image includes text, and where it's located. Used with image tagging, you can then search for images that contain blocks of text. Used with object-aware cropping, you can choose to keep only the text part, or specify a crop that avoids the text.

Parameter	Type	Description
`request` required	{ }object	A JSON object containing request parameters
`async`	◉boolean	Whether to perform the analysis asynchronously. If true, the response is returned immediately and analysis is done in the background. Once complete, a webhook notification will be sent to the specified URL and/or to the URLs defined in the Webhook Notifications settings of your Cloudinary Console.
`notification_url`	Abcstring	The webhook URL to notify when the analysis is complete. Only relevant when async is set to true.
`source` required	{ }object

destructiveidempotentopenWorldreadOnly

Analyze - Coco

Analyze an image using the [Coco](https://cloudinary.com/documentation/cloudinary_ai_content_analysis_addon#ai_based_image_captioning) content-aware detection model. The [Common Objects in Context](https://cocodataset.org/) model contains just 80 common objects.

Parameter	Type	Description
`request` required	{ }object	A JSON object containing request parameters
`async`	◉boolean	Whether to perform the analysis asynchronously. If true, the response is returned immediately and analysis is done in the background. Once complete, a webhook notification will be sent to the specified URL and/or to the URLs defined in the Webhook Notifications settings of your Cloudinary Console.
`notification_url`	Abcstring	The webhook URL to notify when the analysis is complete. Only relevant when async is set to true.
`source` required	{ }object

destructiveidempotentopenWorldreadOnly

Analyze - Google Logo Detection

Detects popular product logos within an image.

Parameter	Type	Description
`request` required	{ }object	A JSON object containing request parameters
`async`	◉boolean	Whether to perform the analysis asynchronously. If true, the response is returned immediately and analysis is done in the background. Once complete, a webhook notification will be sent to the specified URL and/or to the URLs defined in the Webhook Notifications settings of your Cloudinary Console.
`notification_url`	Abcstring	The webhook URL to notify when the analysis is complete. Only relevant when async is set to true.
`source` required	{ }object

destructiveidempotentopenWorldreadOnly

Analyze - Google Tagging

Provides tags for an image using Google's tagging service.

Parameter	Type	Description
`request` required	{ }object	A JSON object containing request parameters
`async`	◉boolean	Whether to perform the analysis asynchronously. If true, the response is returned immediately and analysis is done in the background. Once complete, a webhook notification will be sent to the specified URL and/or to the URLs defined in the Webhook Notifications settings of your Cloudinary Console.
`notification_url`	Abcstring	The webhook URL to notify when the analysis is complete. Only relevant when async is set to true.
`source` required	{ }object

destructiveidempotentopenWorldreadOnly

Analyze - Human Anatomy

Analyze an image using the [Human Anatomy](https://cloudinary.com/documentation/cloudinary_ai_content_analysis_addon#ai_based_image_captioning) content-aware detection model. Cloudinary's human anatomy model identifies parts of the human body in an image. It works best when the majority of a human body is detected in the image.

Parameter	Type	Description
`request` required	{ }object	A JSON object containing request parameters
`async`	◉boolean	Whether to perform the analysis asynchronously. If true, the response is returned immediately and analysis is done in the background. Once complete, a webhook notification will be sent to the specified URL and/or to the URLs defined in the Webhook Notifications settings of your Cloudinary Console.
`notification_url`	Abcstring	The webhook URL to notify when the analysis is complete. Only relevant when async is set to true.
`source` required	{ }object

destructiveidempotentopenWorldreadOnly

Analyze - Image Quality Analysis

Analyze an image using the [Image Quality Analysis](https://cloudinary.com/documentation/cloudinary_ai_content_analysis_addon#image_quality_analysis) model.

Parameter	Type	Description
`request` required	{ }object	A JSON object containing request parameters
`async`	◉boolean	Whether to perform the analysis asynchronously. If true, the response is returned immediately and analysis is done in the background. Once complete, a webhook notification will be sent to the specified URL and/or to the URLs defined in the Webhook Notifications settings of your Cloudinary Console.
`notification_url`	Abcstring	The webhook URL to notify when the analysis is complete. Only relevant when async is set to true.
`source` required	{ }object

destructiveidempotentopenWorldreadOnly

Analyze - Lvis

Analyze an image using the [Lvis](https://cloudinary.com/documentation/cloudinary_ai_content_analysis_addon#ai_based_image_captioning) content-aware detection model. The [Large Vocabulary Instance Segmentation](https://www.lvisdataset.org/) model contains thousands of general objects.

Parameter	Type	Description
`request` required	{ }object	A JSON object containing request parameters
`async`	◉boolean	Whether to perform the analysis asynchronously. If true, the response is returned immediately and analysis is done in the background. Once complete, a webhook notification will be sent to the specified URL and/or to the URLs defined in the Webhook Notifications settings of your Cloudinary Console.
`notification_url`	Abcstring	The webhook URL to notify when the analysis is complete. Only relevant when async is set to true.
`source` required	{ }object

destructiveidempotentopenWorldreadOnly

Analyze - Shop Classifier

Analyze an image using the [Shop Classifier](https://cloudinary.com/documentation/cloudinary_ai_content_analysis_addon#ai_based_image_captioning) content-aware detection model. Cloudinary's shop classifier model detects if the image is a product image taken in a studio, or if it's a natural image.

Parameter	Type	Description
`request` required	{ }object	A JSON object containing request parameters
`async`	◉boolean	Whether to perform the analysis asynchronously. If true, the response is returned immediately and analysis is done in the background. Once complete, a webhook notification will be sent to the specified URL and/or to the URLs defined in the Webhook Notifications settings of your Cloudinary Console.
`notification_url`	Abcstring	The webhook URL to notify when the analysis is complete. Only relevant when async is set to true.
`source` required	{ }object

destructiveidempotentopenWorldreadOnly

Analyze - Unidet

Analyze an image using the [Unidet](https://cloudinary.com/documentation/cloudinary_ai_content_analysis_addon#ai_based_image_captioning) content-aware detection model. The [UniDet](https://github.com/xingyizhou/UniDet) model is a unified model, combining a number of object models, including [Objects365](https://www.objects365.org/overview.html), which focuses on diverse objects in the wild.

Parameter	Type	Description
`request` required	{ }object	A JSON object containing request parameters
`async`	◉boolean	Whether to perform the analysis asynchronously. If true, the response is returned immediately and analysis is done in the background. Once complete, a webhook notification will be sent to the specified URL and/or to the URLs defined in the Webhook Notifications settings of your Cloudinary Console.
`notification_url`	Abcstring	The webhook URL to notify when the analysis is complete. Only relevant when async is set to true.
`source` required	{ }object

destructiveidempotentopenWorldreadOnly

Analyze - Watermark Detection

Analyze an image using the [Watermark Detection](https://cloudinary.com/documentation/cloudinary_ai_content_analysis_addon#watermark_detection) detection model.

Parameter	Type	Description
`request` required	{ }object	A JSON object containing request parameters
`async`	◉boolean	Whether to perform the analysis asynchronously. If true, the response is returned immediately and analysis is done in the background. Once complete, a webhook notification will be sent to the specified URL and/or to the URLs defined in the Webhook Notifications settings of your Cloudinary Console.
`notification_url`	Abcstring	The webhook URL to notify when the analysis is complete. Only relevant when async is set to true.
`source` required	{ }object

destructiveidempotentopenWorldreadOnly

Get analysis task status

Get the status of an analysis task.

Parameter	Type	Description
`task_id` required	Abcstring	The ID of the analysis task