Get multiple values from the cache (alias for get_many).
AI agents call cache_get_multi to retrieve information from Awslabs Valkey without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves cached data without modification, deletion, or external execution. It is a standard cache read operation that queries existing data and returns results. No data is created, modified, deleted, or financial commitments are made. This is a straightforward Read category tool with low severity—misuse would only expose cached data that may already be accessible through other means.
From the tool's definition Tool description states "Get multiple values from the cache" which is a retrieval operation with no side effects. The alias reference "get_many" further confirms this is a multi-key read operation.
Attacks that exploit this kind of access
Get multiple values from the cache (alias for get_many). It is categorised as a Read tool in the Awslabs Valkey MCP Server, which means it retrieves data without modifying state.
Register the Awslabs Valkey MCP server in PolicyLayer and add a rule for cache_get_multi: 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 Awslabs Valkey. Nothing to install.
cache_get_multi 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_get_multi 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_get_multi. 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_get_multi is provided by the Awslabs Valkey MCP server (awslabs.valkey-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.