AI agents call get_partition_health_history 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 retrieves and analyzes existing partition health state data (transitions, flapping detection) without creating, modifying, deleting, or executing any operations on the Kafka cluster. It is a pure read operation analogous to monitoring/observability queries. The blast radius of misuse is minimal—an AI agent could over-query or request excessive data, but cannot damage the cluster or cause side effects.
From the tool's definition Tool name and description indicate data retrieval only: 'Track partition online/offline transitions and identify flapping partitions' — queries historical health status with no modification, deletion, or execution of cluster operations.
Attacks that exploit this kind of access
Track partition online/offline transitions and identify flapping partitions. 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_partition_health_history: 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_partition_health_history 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_partition_health_history 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_partition_health_history. 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_partition_health_history 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 →