consumer_group_lag
AI agents call consumer_group_lag to retrieve information from Kafka MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Consumer group lag is a monitoring metric that queries the state of Kafka consumer groups—how far behind they are processing messages. This is a non-destructive, read-only operation with no side effects. It retrieves information for inspection purposes only, placing it squarely in the Read category.
From the tool's definition Tool name 'consumer_group_lag' indicates retrieval of consumer group lag metrics. Sibling tools like 'list_consumer_groups', 'list_topics', and 'live_messages' are all Read operations.
Attacks that exploit this kind of access
consumer_group_lag. It is categorised as a Read tool in the Kafka MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Kafka MCP Server MCP server in PolicyLayer and add a rule for consumer_group_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 Kafka MCP Server. Nothing to install.
consumer_group_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 consumer_group_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 consumer_group_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.
consumer_group_lag is provided by the Kafka MCP Server MCP server (jilanisayyad/kafka-mcp-server). 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 →