Cloudinary Structured Metadata
Connect AI tools to Cloudinary’s structured metadata (SMD) with the Cloudinary Structured Metadata MCP server. Use natural language to define and manage metadata fields, set values on assets, and configure conditional metadata rules—so you can enrich and govern your media schema without writing code.
1. Overview
Cloudinary Structured Metadata 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://structured-metadata.mcp.cloudinary.com/sse - Transport: SSE (Server-Sent Events)
- Hosted by: Cloudinary
It is part of Cloudinary’s MCP server suite for managing structured metadata. Use it to create metadata fields, assign values, and define rules that apply metadata conditionally (e.g. by asset type, folder, or tag).
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 Structured Metadata 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 Structured Metadata MCP server, you can:
- Define metadata fields — Create structured metadata field definitions (e.g. string, number, date, set) for your media.
- Manage values — Set, update, or clear metadata values on assets.
- Conditional metadata rules — Define rules that automatically apply or update metadata based on conditions (e.g. when asset type is image and folder is ‘products’, set field ‘category’ to ‘product’).
- Schema governance — Keep metadata consistent across folders, asset types, or tags.
This server is ideal for DAM-style workflows, product catalogs, and any use case where consistent, queryable metadata is important.
4. Prerequisites
Before adding Cloudinary Structured Metadata in Cequence AI Gateway, ensure you have:
- Access to Cequence AI Gateway (e.g. beta.aigateway.cequence.ai)
- A Cloudinary account with access to structured metadata features
- 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
- Create field: “Add a structured metadata field called ‘campaign_id’ of type string and make it required for the ‘campaigns’ folder.”
- Set values: “Set the metadata field ‘category’ to ‘hero’ for all assets in the folder ‘homepage/hero’.”
- Conditional rule: “Create a rule: when an asset is tagged ‘product’, set the metadata field ‘type’ to ‘product-image’.”
- Bulk update: “List all assets that have the metadata field ‘status’ and set it to ‘approved’ where it’s currently ‘pending’.”
- Multi-step: “Create a new metadata field ‘season’, then run through all assets in ‘campaigns/2025’ and set ‘season’ to ‘2025’.”
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 Structured Metadata 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: Use with Cloudinary Asset Management to tag and organize assets, and with Cloudinary Analysis to drive metadata from AI (e.g. auto-tag then set structured fields). See also Cloudinary Environment Config for presets and transformations.
- Official documentation: For MCP setup and Cloudinary structured metadata concepts, see Cloudinary MCP Server (blog) and Cloudinary LLM & MCP documentation.