Delete a category from Kaltura
AI agents call kaltura.category.delete to permanently remove resources in Kaltura MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a category in Kaltura is a destructive, likely irreversible action. Categories organize media content, so removing one could affect all media entries associated with it, potentially disrupting content organization across the platform. The blast radius is high because a misused delete could cascade across many media entries.
From the tool's definition "Delete a category from Kaltura" — explicitly deletes a category, which is an irreversible removal of a structural organizational element
Attacks that exploit this kind of access
Delete a category from Kaltura. It is categorised as a Destructive tool in the Kaltura MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Kaltura MCP Server MCP server in PolicyLayer and add a rule for kaltura.category.delete: 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 Kaltura MCP Server. Nothing to install.
kaltura.category.delete is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the kaltura.category.delete 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 kaltura.category.delete. 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.
kaltura.category.delete is provided by the Kaltura MCP Server MCP server (zoharbabin/kaltura-mcp-legacy). 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 →