Search for existing files (assets) in Cloudinary with a query expression
AI agents call find-assets to retrieve information from Cloudinary without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries data about existing assets without side effects. It performs a search operation, which is a classic read action. There is no capability to modify, delete, or execute arbitrary operations—only to discover and list assets matching criteria.
From the tool's definition Tool name 'find-assets' and description 'Search for existing files (assets) in Cloudinary with a query expression' indicates a query/search operation with no modification or deletion of data.
Attacks that exploit this kind of access
Search for existing files (assets) in Cloudinary with a query expression. It is categorised as a Read tool in the Cloudinary MCP Server, which means it retrieves data without modifying state.
Register the Cloudinary MCP server in PolicyLayer and add a rule for find-assets: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Cloudinary. Nothing to install.
find-assets is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the find-assets rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for find-assets. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
find-assets is provided by the Cloudinary MCP server (yoavniran/cloudinary-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →