Critical Risk →

stream_group_delete_consumer

Delete consumer from group. Args: key: The name of the key group_name: Name of consumer group consumer_name: Name of consumer to delete Returns: Success message or error message

How to control stream_group_delete_consumer ↓

What stream_group_delete_consumer does on AWS

AI agents call stream_group_delete_consumer to permanently remove resources in AWS — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

Critical Risk

Why stream_group_delete_consumer needs a policy

The tool performs an irreversible deletion operation ('delete consumer from group'). Once executed, the consumer is removed and cannot be recovered without re-adding it manually. This is a destructive action that modifies system state permanently.

From the tool's definition Tool name contains 'delete'; description states 'Delete consumer from group.' This is an irreversible removal of a consumer entity from a Kafka/stream processing group.

Documented attack patterns abuse exactly the kind of access stream_group_delete_consumer gives an agent:

How to control stream_group_delete_consumer

PolicyLayer is an MCP gateway — it sits between your AI agents and AWS, and nothing reaches the server without passing your rules. This is the rule we recommend for stream_group_delete_consumer:

policy.json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "stream_group_delete_consumer"
  ]
}

stream_group_delete_consumer disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

  1. Create a free account and register AWS — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
RESTRICT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about stream_group_delete_consumer

What does the stream_group_delete_consumer tool do? +

Delete consumer from group. Args: key: The name of the key group_name: Name of consumer group consumer_name: Name of consumer to delete Returns: Success message or error message. It is categorised as a Destructive tool in the AWS MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on stream_group_delete_consumer? +

Register the AWS MCP server in PolicyLayer and add a rule for stream_group_delete_consumer: 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 AWS. Nothing to install.

What risk level is stream_group_delete_consumer? +

stream_group_delete_consumer is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit stream_group_delete_consumer? +

Yes. Add a rate_limit block to the stream_group_delete_consumer 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.

How do I block stream_group_delete_consumer completely? +

Set action: deny in the PolicyLayer policy for stream_group_delete_consumer. 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.

What MCP server provides stream_group_delete_consumer? +

stream_group_delete_consumer is provided by the AWS MCP server (@awslabs/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every AWS tool call.

Start from AWS, 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.

300 AWS tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.