AI agents call kafka_list_consumer_groups to retrieve information from MCP Kafka without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays information about consumer groups (their state and protocol type) without creating, modifying, or deleting any data. It is a read-only query operation with no side effects, making it the least risky category. The low severity reflects minimal blast radius even if an AI agent calls it without restriction.
From the tool's definition Tool name 'kafka_list_consumer_groups' and description 'List all consumer groups with their state and protocol type' indicate a retrieval operation that queries cluster metadata without modifying state.
Attacks that exploit this kind of access
List all consumer groups with their state and protocol type. It is categorised as a Read tool in the MCP Kafka MCP Server, which means it retrieves data without modifying state.
Register the MCP Kafka MCP server in PolicyLayer and add a rule for kafka_list_consumer_groups: 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 MCP Kafka. Nothing to install.
kafka_list_consumer_groups 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 kafka_list_consumer_groups 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 kafka_list_consumer_groups. 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.
kafka_list_consumer_groups is provided by the MCP Kafka MCP server (williajm/mcp_kafka). 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 →