AI agents call kafka_cluster_info to retrieve information from MCP Kafka without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only queries and returns cluster information without creating, modifying, deleting, or executing any operations. It has no side effects and poses minimal risk if misused by an AI agent, as the worst outcome would be information disclosure about cluster topology, which is typically non-sensitive operational metadata.
From the tool's definition Tool retrieves cluster metadata (cluster ID, controller, broker/topic counts) with no modification of data or side effects. Description explicitly indicates this is a get operation for informational purposes only.
Attacks that exploit this kind of access
Get Kafka cluster metadata (cluster ID, controller, broker/topic counts). It is categorised as a Read tool in the MCP Kafka MCP Server, which means it retrieves data without modifying state.
Register the MCP Kafka MCP server in PolicyLayer and add a rule for kafka_cluster_info: 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 MCP Kafka. Nothing to install.
kafka_cluster_info 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 kafka_cluster_info 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 kafka_cluster_info. 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.
kafka_cluster_info is provided by the MCP Kafka MCP server (williajm/mcp_kafka). 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 →