AI agents use create_topic 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.
Creating a topic is a reversible write operation that adds a new messaging resource. While it doesn't delete data, it modifies cloud infrastructure state and could incur costs or enable unwanted messaging channels. The empty description reduces confidence slightly, but the name and AWS context clearly indicate a resource creation operation rather than read, destructive, execute, or financial action.
From the tool's definition Tool name 'create_topic' suggests creation of a messaging topic (likely SNS or similar AWS service). Combined with sibling tools indicating AWS infrastructure management (policies, users, groups, audit functions), this tool creates a new resource.
Documented attack patterns abuse exactly the kind of access create_topic 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 create_topic:
{
"version": "1",
"default": "deny",
"tools": {
"create_topic": {
"limits": [
{
"counter": "create_topic_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_topic 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.
create_topic. 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 create_topic: 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.
create_topic 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 create_topic 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 create_topic. 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.
create_topic 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.