Cloudinary stores, transforms, and delivers images and video for many web and mobile properties. Connecting Cloudinary to clariBI surfaces every asset, transformation, and folder inside your AI analyses, so creative-ops questions about storage growth, tag coverage, and asset reuse get direct answers.
Why connect Cloudinary
Cloudinary dashboards show storage and bandwidth in aggregate but rarely answer specific questions like "which assets are eating most of our quota?" or "what percentage of images are missing alt-text metadata?". Those usually require CSV exports.
With Cloudinary connected, you can ask "How much storage did we use last quarter and what is the trend?", "Find untagged images uploaded in the last 30 days", or "Which folders hold the largest assets?" and the AI engine pulls the answer with the relevant assets referenced.
How the connection works
clariBI talks to Cloudinary through its hosted MCP server at https://asset-management.mcp.cloudinary.com/sse. Authentication uses an OAuth flow that clariBI registers itself for (no developer console setup on your side). Tokens stay encrypted server-side and never leave clariBI in clear form.
sequenceDiagram
actor U as You
participant C as clariBI
participant V as Cloudinary
U->>C: Click Authorize with Cloudinary
C->>V: Open OAuth authorization
V-->>U: Grant read access?
U->>V: Approve
V-->>C: Authorization code
C->>V: Exchange code for tokens
V-->>C: Access + refresh tokens
C->>C: Encrypt and store credentials
C-->>U: Connection ready
Available tools
clariBI exposes the read-only Cloudinary tools that the vendor's MCP server publishes at connection time. Write operations (create, update, delete, send, refund) are filtered out by a name-pattern blocklist before any tool reaches the analysis engine, so connecting Cloudinary cannot modify data on the vendor side.
The exact tool inventory depends on the Cloudinary features your account has access to. After connecting, try a few natural-language questions to see what Cloudinary data clariBI can pull.
Data flow during analysis
When you ask a question that maps to Cloudinary, the AI engine routes to the right tool, reads the result, and pairs the answer with a chart you can pin to a dashboard.
sequenceDiagram
actor U as You
participant C as clariBI
participant AI as AI engine
participant V as Cloudinary
U->>C: Ask a question about media asset metadata
C->>AI: Plan the analysis
AI->>V: Call the right tool
V-->>AI: Tool result
AI->>AI: Summarize and chart
C-->>U: Answer plus visual
Setting up the connection
- Open Data Sources in the clariBI sidebar.
- Click Add data source.
- Open the MCP Servers tab.
- Click the Cloudinary card.
- Click Authorize with Cloudinary.
- Sign in to Cloudinary in the popup window and grant the requested read scopes.
- Back in clariBI, give your data source a name.
- Click Finish.
Permissions and data access
clariBI requests the resource:read scope. No assets can be uploaded, modified, deleted, or transformed. Folder permissions in Cloudinary still apply, so users only see assets their Cloudinary role allows. Disconnect anytime from Cloudinary account settings or from clariBI Settings.
Troubleshooting
| Error | Cause | Fix |
|---|---|---|
| "Cloud name mismatch" | Your Cloudinary account has multiple cloud names and the one selected during authorization is different from the one you expected. | Reconnect and pick the right cloud name in the Cloudinary authorization screen. |
| "Asset list returns empty" | The folder filter applied by the AI engine matched no assets in the selected cloud. | Broaden the question or check folder names in your Cloudinary Media Library. |