AI agents use create_kafka_topic to create or update resources in KafkaIQ — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your KafkaIQ environment.
Creating a Kafka topic adds a new resource to the cluster configuration, which is reversible through deletion. This is a Write operation rather than Execute because it creates a specific resource rather than executing arbitrary code or queries. It is not Destructive since topic creation can be undone.
From the tool's definition Tool name 'create_kafka_topic' indicates creation of a Kafka topic, which is a write operation that modifies cluster configuration. The description is empty, reducing confidence slightly.
Attacks that exploit this kind of access
create_kafka_topic. It is categorised as a Write tool in the KafkaIQ MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the KafkaIQ MCP server in PolicyLayer and add a rule for create_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.
create_kafka_topic is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_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 create_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.
create_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 →