AI agents call stream_group_destroy to permanently remove resources in Finch MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Destroying a consumer group is an irreversible operation that permanently removes the group and any associated offsets/state. This falls clearly into the Destructive category with high severity due to the potential loss of consumer tracking data and inability to undo the action.
From the tool's definition 'Destroy consumer group' — 'destroy' indicates irreversible deletion of the consumer group and its state
Documented attack patterns abuse exactly the kind of access stream_group_destroy gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Finch MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for stream_group_destroy:
{
"version": "1",
"default": "deny",
"hide": [
"stream_group_destroy"
]
} stream_group_destroy disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Destroy consumer group. It is categorised as a Destructive tool in the Finch MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Finch MCP Server MCP server in PolicyLayer and add a rule for stream_group_destroy: 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 Finch MCP Server. Nothing to install.
stream_group_destroy is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the stream_group_destroy 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 stream_group_destroy. 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.
stream_group_destroy is provided by the Finch MCP Server MCP server (awslabs.finch-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Finch MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
805 Finch MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.