Read entries from stream as part of consumer group. Args: key: The name of the key group_name: Name of consumer group consumer_name: Name of this consumer count: Maximum number of entries to return block: Milliseconds to block (optional) noack: Don't require acknowledgment Returns: List of entrie...
AI agents call stream_read_group to retrieve information from AWS without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data from a stream without side effects. The 'noack' parameter controls acknowledgment behavior but does not modify the underlying data. It is a passive read operation typical of consumer group patterns in message queues and streams. No data is created, modified, deleted, or financial operations are performed.
From the tool's definition Tool name contains 'read'; description states 'Read entries from stream as part of consumer group' with no modification, deletion, or execution capabilities.
Documented attack patterns abuse exactly the kind of access stream_read_group gives an agent:
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_read_group:
{
"version": "1",
"default": "deny",
"tools": {
"stream_read_group": {}
}
}stream_read_group is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Read entries from stream as part of consumer group. Args: key: The name of the key group_name: Name of consumer group consumer_name: Name of this consumer count: Maximum number of entries to return block: Milliseconds to block (optional) noack: Don't require acknowledgment Returns: List of entries or error message. It is categorised as a Read tool in the AWS MCP Server, which means it retrieves data without modifying state.
Register the AWS MCP server in PolicyLayer and add a rule for stream_read_group: 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.
stream_read_group 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 stream_read_group 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_read_group. 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_read_group 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.
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.