stream_group_create
AI agents use stream_group_create to create or update resources in AWS — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AWS environment.
The tool creates a new group (reversible via deletion). This is a Write operation rather than Read (no retrieval), Execute (no code execution), or Destructive (creation is reversible). Severity is high because creating groups in AWS access control systems can grant permissions to multiple users and impact security posture, though the impact is bounded by the specific group created.
From the tool's definition Tool name 'stream_group_create' indicates creation of a group resource. Sibling tools include 'add_user_to_group', 'attach_group_policy', 'attach_user_policy', suggesting this server manages AWS IAM/access control resources.
Documented attack patterns abuse exactly the kind of access stream_group_create 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_group_create:
{
"version": "1",
"default": "deny",
"tools": {
"stream_group_create": {
"limits": [
{
"counter": "stream_group_create_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}stream_group_create stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
stream_group_create. It is categorised as a Write tool in the AWS MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AWS MCP server in PolicyLayer and add a rule for stream_group_create: 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_group_create is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the stream_group_create 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_create. 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_create 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.