Delete a Kafka topic.
AI agents call delete_kafka_topic to permanently remove resources in KafkaIQ — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a Kafka topic removes all associated data streams and configurations permanently. This is an irreversible destructive action that eliminates production data and disables any consumers or producers relying on that topic. The blast radius is high as unintended deletion could cause severe operational disruption to dependent systems.
From the tool's definition Tool name explicitly states 'delete_kafka_topic' and description confirms 'Delete a Kafka topic.' Deletion of a Kafka topic is irreversible and cannot be undone.
Attacks that exploit this kind of access
Delete a Kafka topic. It is categorised as a Destructive tool in the KafkaIQ MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the KafkaIQ MCP server in PolicyLayer and add a rule for delete_kafka_topic: 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 KafkaIQ. Nothing to install.
delete_kafka_topic 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 delete_kafka_topic 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 delete_kafka_topic. 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.
delete_kafka_topic is provided by the KafkaIQ MCP server (ojhaayush03/kafka_mcp). 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 →