最近の記憶を新しい順に返す。
AI agents call get_recent_memories to retrieve information from Memory Engine without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and lists stored memory records in chronological order. It performs a query operation that does not create, modify, delete, or execute any code—it only reads and returns existing data. The blast radius of misuse is minimal: an agent could recall previously stored information but cannot alter, destroy, or execute actions. This is a classic Read category tool.
From the tool's definition Tool name 'get_recent_memories' and description 'Returns recent memories in newest-first order' (translated from Japanese) indicates a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
最近の記憶を新しい順に返す。. It is categorised as a Read tool in the Memory Engine MCP Server, which means it retrieves data without modifying state.
Register the Memory Engine MCP server in PolicyLayer and add a rule for get_recent_memories: 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 Memory Engine. Nothing to install.
get_recent_memories 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 get_recent_memories 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 get_recent_memories. 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.
get_recent_memories is provided by the Memory Engine MCP server (kagioneko/memory-engine-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →