AI agents call get_consumer_lag 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 queries consumer lag metrics from Kafka clusters—a read-only operation that reports on consumer group status. There are no side effects, no data modifications, no code execution, and no destructive actions. While the information could be sensitive in some contexts, the primary function is informational monitoring, which is characteristic of the Read category.
From the tool's definition The tool name 'get_consumer_lag' and description 'Get consumer lag information for a specific consumer group and topic' indicate a data retrieval operation with the verb 'Get', which queries existing metrics without modifying or executing operations.
Attacks that exploit this kind of access
Get consumer lag information for a specific consumer group and topic. 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_consumer_lag: 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_consumer_lag 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_consumer_lag 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_consumer_lag. 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_consumer_lag 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 →