Cloudinary Asset Management
Connect AI tools to Cloudinary to upload and manage images, videos, and raw files with natural language. The Cloudinary Asset Management MCP server gives AI assistants programmatic access to your media library with advanced search, filtering, folders, and tags—so you can organize, rename, delete, and retrieve assets without writing code.
1. Overview
Cloudinary Asset Management 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://asset-management.mcp.cloudinary.com/sse - Transport: SSE (Server-Sent Events)
- Hosted by: Cloudinary
It is part of Cloudinary’s MCP server suite for managing visual media assets. Use it to automate uploads, organize media by tags and folders, and run search and retrieval tasks from your preferred AI client.
2. Supported authentication types
| Type | Supported | Notes |
|---|---|---|
| OAuth 2.0 | Yes | Required. Uses Dynamic Client Registration (DCR); sign in with your Cloudinary account. |
| API key | No | Not used for this remote MCP server. |
When you add Cloudinary Asset Management 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 Asset Management MCP server, you can:
- Upload images, videos, and raw files to specific folders or locations in Cloudinary.
- Search and filter assets using advanced search (e.g. by tag, type, folder).
- Organize media using folders and tags; move or rename assets.
- Delete or archive assets as part of cleanup or lifecycle workflows.
- Retrieve assets using natural language (e.g. “Retrieve all image assets with the tag ‘car’”).
This server exposes Cloudinary’s upload and Admin API capabilities so LLMs can chain operations like upload → tag → transform → delivery URL in live tasks or scripts.
4. Prerequisites
Before adding Cloudinary Asset Management 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 media you want to manage
- 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
- Organize by tag: “Find all assets with the tag ‘holiday2025’ and move them to the folder ‘holiday2025_campaign’.”
- Upload and tag: “Upload this image to the folder ‘campaigns/spring’ and tag it with ‘spring2025’ and ‘hero’.”
- Search and report: “Retrieve all image assets with the tag ‘car’ and list their public IDs and formats.”
- Cleanup: “List all assets in the ‘archive’ folder that are older than 90 days and delete them.”
- Multi-step: “Upload this file, tag it with ‘product-shot’, apply the ‘thumbnail’ named transformation, and give me the delivery URL.”
6. Connecting MCP server from Cequence AI Gateway
- Log in to Cequence AI Gateway.
- Choose your tenant.
- Go to App catalogue.
- Filter by Remote MCP server.
- Search for Cloudinary Asset Management and then select it.
- Click Create MCP server.
- Choose auth method. If OAuth, you need an auth app with client credentials in your vendor account (see Prerequisites).
- 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
- Transport: This server uses SSE (Server-Sent Events), not HTTP. The gateway and client must support SSE for the connection.
- Timeout: The remote server uses a 30-second timeout for requests.
- Part of Cloudinary MCP suite: You can combine this server with Cloudinary Analysis, Cloudinary Environment Config, and Cloudinary Structured Metadata for full media workflows.
- Official documentation: For MCP setup, tutorials, and IDE configuration, see Cloudinary MCP Server (blog) and Cloudinary LLM & MCP documentation.