Can I use Cloudinary as a CLI?

Yes. KosmoKrator exposes a Cloudinary CLI through kosmo integrations:call and the provider shortcut command. Commands can return JSON for scripts, CI, and coding agents.

Can I expose Cloudinary through MCP?

Yes. The KosmoKrator MCP gateway can expose selected Cloudinary tools to clients such as Claude Code, Cursor, Codex, and other MCP-compatible tools.

Where are Cloudinary credentials stored?

Cloudinary credentials are configured in KosmoKrator's local integration settings and reused by CLI, Lua, and MCP gateway surfaces.

Can I deny write access for Cloudinary MCP tools?

Yes. Start the gateway with --write=deny for read-only clients, or use ask/allow only for trusted workspaces.

other

Cloudinary MCP Integration for Vercel AI SDK

Connect Cloudinary to Vercel AI SDK through the local KosmoKrator MCP gateway with scoped tools, credentials, and write policy.

6 functions 4 read 2 write Manual OAuth token auth

Submit Cloudinary feedback View package source

Connect Cloudinary to Vercel AI SDK

Use KosmoKrator as a local integration gateway for Vercel AI SDK agents and scripts.

Create an MCP client that starts or connects to the KosmoKrator gateway for the selected integration. The gateway is local, scoped to this integration, and starts with --write=deny so Vercel AI SDK can inspect read-capable tools without receiving write access by default.

Cloudinary MCP Config for Vercel AI SDK

Prefer CLI JSON calls when a workflow only needs one deterministic integration operation.

{
  "mcpServers": {
    "kosmokrator-cloudinary": {
      "type": "stdio",
      "command": "kosmo",
      "args": [
        "mcp:serve",
        "--integration=cloudinary",
        "--write=deny"
      ]
    }
  }
}

Run the Gateway Manually

kosmokrator mcp:serve --integration=cloudinary --write=deny

Why Use KosmoKrator Here

Scoped tools

Expose only Cloudinary instead of a broad multi-service tool list.

Local credentials

Reuse credentials already configured for the KosmoKrator CLI and Lua runtime.

Write policy

Start read-only, then opt into ask or allow for trusted workspaces.

Cloudinary Tools Visible to Vercel AI SDK

Vercel AI SDK sees stable MCP tool names generated from the Cloudinary integration catalog.

MCP tool	Source function	Type	Description
`integration__cloudinary__cloudinary_upload`	`cloudinary.cloudinary_upload`	Write	Upload an image to Cloudinary. Provide a file URL or base64 data URI, an optional public ID, and an optional folder path. Returns the uploaded asset details.
`integration__cloudinary__cloudinary_list_resources`	`cloudinary.cloudinary_list_resources`	Read	List media resources in your Cloudinary cloud. Filter by resource type (image, video, raw) and prefix. Supports pagination with max_results and next_cursor.
`integration__cloudinary__cloudinary_get_resource`	`cloudinary.cloudinary_get_resource`	Read	Get details of a specific Cloudinary resource by its type and public ID. Returns full asset metadata including dimensions, format, URL, tags, and derived resources.
`integration__cloudinary__cloudinary_delete_resource`	`cloudinary.cloudinary_delete_resource`	Write	Delete a media resource from Cloudinary by its type and public ID. This permanently removes the asset and all its derived resources.
`integration__cloudinary__cloudinary_list_folders`	`cloudinary.cloudinary_list_folders`	Read	List all folders in your Cloudinary cloud. Returns folder names and paths with pagination support.
`integration__cloudinary__cloudinary_get_current_user`	`cloudinary.cloudinary_get_current_user`	Read	Get the currently authenticated Cloudinary user profile. Returns user name, email, and account details. Use this to verify that credentials are working.

Related Cloudinary Pages

Cloudinary CLIUse direct JSON commands instead of MCP discovery. Cloudinary MCPFull gateway reference and MCP tool names. KosmoKrator for Vercel AI SDKClient-level gateway setup.