AI agents call stream_read 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.
The name 'stream_read' strongly suggests a retrieval operation with no side effects. However, confidence is moderate (0.7) rather than high because the description is empty, and without it, the exact scope and blast radius cannot be fully determined. The context of AWS tools and siblings like 'audit_' functions suggests this is likely a benign read operation.
From the tool's definition Tool name 'stream_read' indicates a read operation on a stream or data source. No destructive, write, or execute keywords present.
Documented attack patterns abuse exactly the kind of access stream_read 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:
{
"version": "1",
"default": "deny",
"tools": {
"stream_read": {}
}
}stream_read 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.
stream_read. 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: 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 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 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. 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 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.