Get a value and its CAS token from the cache. Args: key: The key to retrieve Returns: Value and CAS token or error message
AI agents call cache_gets 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 is a simple cache retrieval operation that queries and returns a value along with its CAS (Compare-And-Swap) token. It performs no write, delete, execute, or financial operations. The retrieval of cached data poses minimal security risk on its own, though sensitivity depends on what data is cached. Confidence is high based on clear 'Get' semantics in the description.
From the tool's definition Tool description states: 'Get a value and its CAS token from the cache.' The operation retrieves data (get) with no modification or side effects.
Documented attack patterns abuse exactly the kind of access cache_gets 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 cache_gets:
{
"version": "1",
"default": "deny",
"tools": {
"cache_gets": {}
}
}cache_gets 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.
Get a value and its CAS token from the cache. Args: key: The key to retrieve Returns: Value and CAS token 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 cache_gets: 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.
cache_gets 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 cache_gets 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 cache_gets. 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.
cache_gets 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.