AI agents use create_datastore 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 performs a reversible creation/modification action (Write category) rather than irreversible deletion or financial operations. Severity is medium because creating unauthorized datastores could lead to resource sprawl, cost implications, or data exposure, but the action itself is not immediately destructive.
From the tool's definition Tool name 'create_datastore' indicates creation of a data storage resource. On AWS, creating datastores typically creates persistent data storage resources (databases, tables, buckets, etc.) that can be modified or deleted later.
Documented attack patterns abuse exactly the kind of access create_datastore 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_datastore:
{
"version": "1",
"default": "deny",
"tools": {
"create_datastore": {
"limits": [
{
"counter": "create_datastore_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_datastore 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_datastore. 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_datastore: 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_datastore 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_datastore 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_datastore. 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_datastore 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.