AI agents call get_cluster_details 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.
The tool retrieves and queries cluster metadata and health status without creating, modifying, deleting, or executing any operations. It has no side effects and poses minimal risk as it only exposes existing cluster information for monitoring purposes.
From the tool's definition Tool name 'get_cluster_details' and description 'Get comprehensive cluster health and metadata information' indicate a retrieval operation with no modification or execution of commands. This is a read-only query of cluster state.
Attacks that exploit this kind of access
Get comprehensive cluster health and metadata information. 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 get_cluster_details: 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.
get_cluster_details 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 get_cluster_details 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 get_cluster_details. 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.
get_cluster_details 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 →