Skip to main content

Cloudinary Analysis

Connect AI tools to Cloudinary’s AI-powered content analysis with the Cloudinary Analysis MCP server. Use natural language to run automatic tagging, content moderation, safety checks, object detection, and recognition on your media—so you can categorize, moderate, and enrich assets without writing code.

1. Overview​

Cloudinary Analysis is a remote, vendor-hosted MCP server provided by Cloudinary. You connect to it from Cequence AI Gateway; the server runs in the cloud and uses SSE (Server-Sent Events) for real-time communication.

  • Server URL: https://analysis.mcp.cloudinary.com/sse
  • Transport: SSE (Server-Sent Events)
  • Hosted by: Cloudinary

It is part of Cloudinary’s MCP server suite for AI-powered content analysis. Use it to automate tagging, moderation workflows, and media insights from your preferred AI client.

2. Supported authentication types​

TypeSupportedNotes
OAuth 2.0YesRequired. Uses Dynamic Client Registration (DCR); sign in with your Cloudinary account.
API keyNoNot used for this remote MCP server.

When you add Cloudinary Analysis in Cequence AI Gateway, authentication is handled via OAuth 2.0 with Dynamic Client Registration. You sign in with your Cloudinary account and grant access during the gateway flow.

3. What can you do with this MCP server​

With the Analysis MCP server, you can:

  • Automatic tagging — Apply AI-generated tags to images and videos for better search and organization.
  • Content moderation — Run moderation checks on uploads or existing assets (e.g. safe for work, policy compliance).
  • Safety checks — Use built-in safety and quality checks on media.
  • Object detection and recognition — Detect and recognize objects, scenes, or entities in assets for categorization and retrieval.
  • Media insights — Uncover assets based on metadata and tags and get suggestions to improve organization or delivery.

This server is ideal for automating e-commerce image categorization, moderation pipelines, and content enrichment workflows.

4. Prerequisites​

Before adding Cloudinary Analysis in Cequence AI Gateway, ensure you have:

  • Access to Cequence AI Gateway (e.g. beta.aigateway.cequence.ai)
  • A Cloudinary account with access to the product and, if required, any AI/analysis add-ons (e.g. AI Vision)
  • A modern browser to complete the OAuth authorization flow
  • For OAuth authentication: an auth app with client credentials (client ID and client secret) in your Cloudinary (vendor) account, unless the server supports Dynamic Client Registration (DCR).

5. Example workflows​

  • Auto-tag uploads: “Analyze the last 10 uploaded images and add AI-generated tags to each.”
  • Moderation: “Run content moderation on all assets in the folder ‘user-uploads’ and list any that need review.”
  • Categorization: “Detect objects in all product images in ‘products/’ and tag them by category (e.g. clothing, electronics).”
  • Insights: “Uncover all images with metadata indicating ‘outdoor’ and suggest how to improve their tags for search.”
  • Multi-step: “Upload this image, run object detection, add the detected labels as tags, and then move it to the folder that matches the primary tag.”

6. Connecting MCP server from Cequence AI Gateway​

  1. Log in to Cequence AI Gateway.
  2. Choose your tenant.
  3. Go to App catalogue.
  4. Filter by Remote MCP server.
  5. Search for Cloudinary Analysis and then select it.
  6. Click Create MCP server.
  7. Choose auth method. If OAuth, you need an auth app with client credentials in your vendor account (see Prerequisites).
  8. Complete the setup as prompted, select tools, and deploy.

Use the generated MCP server URL in your client as described in the Client Configuration docs. For detailed UI steps and screenshots, see Create a third-party MCP Server.

7. Additional information​