AI agents call get_offline_partitions 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 reports status information about Kafka cluster partitions. It performs a read-only query of cluster metadata and does not create, modify, delete, or execute any operations. The information returned is diagnostic in nature and used for monitoring health. Misuse carries minimal risk—an AI agent cannot cause harm by repeatedly querying partition status.
From the tool's definition Tool name 'get_offline_partitions' and description 'Returns all offline partitions' indicate a pure retrieval operation with no side effects. The function queries cluster state to identify partitions without an assigned leader.
Attacks that exploit this kind of access
Returns all offline partitions (leader == -1). 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_offline_partitions: 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_offline_partitions 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_offline_partitions 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_offline_partitions. 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_offline_partitions 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 →