AI agents call list_kafka_topics to retrieve information from KafkaIQ without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns information about existing Kafka topics without creating, modifying, deleting, or executing any operations. It is a passive read-only operation that retrieves cluster metadata. The blast radius of misuse is minimal—an AI agent listing topics poses no risk to cluster integrity, data, or operations.
From the tool's definition Tool name 'list_kafka_topics' and description 'List all topics in the Kafka cluster' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
List all topics in the Kafka cluster. It is categorised as a Read tool in the KafkaIQ MCP Server, which means it retrieves data without modifying state.
Register the KafkaIQ MCP server in PolicyLayer and add a rule for list_kafka_topics: 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.
list_kafka_topics 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 list_kafka_topics 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 list_kafka_topics. 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.
list_kafka_topics 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 →