Fetch committed offsets for a consumer group.
AI agents call get_group_offsets 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.
This tool retrieves consumer group offset information, which is a query/fetch operation with no side effects. It does not create, modify, delete, or execute code. The blast radius of misuse is minimal—an agent could only access information about consumer group progress, not disrupt message flow or delete data.
From the tool's definition Tool name 'get_group_offsets' and description 'Fetch committed offsets for a consumer group' indicate a read-only query operation that retrieves metadata about consumer group state without modifying, deleting, or executing operations.
Attacks that exploit this kind of access
Fetch committed offsets for a consumer group. 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 get_group_offsets: 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.
get_group_offsets 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_group_offsets 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_group_offsets. 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_group_offsets is provided by the Kafka MCP Server MCP server (shivamxtech/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 →