最近のセッション要約を返す。新しいセッション開始時に前回の文脈を確認するために使う。
AI agents call get_recent_summaries 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 queries stored session summary data without modifying, deleting, or executing operations. It is a straightforward read operation that retrieves historical context. No side effects beyond data retrieval occur. Severity is low as unauthorized access to summaries poses minimal risk compared to destructive or financial operations.
From the tool's definition Tool name 'get_recent_summaries' and description indicating it returns recent session summaries for context review at session start.
Attacks that exploit this kind of access
最近のセッション要約を返す。新しいセッション開始時に前回の文脈を確認するために使う。. 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_summaries: 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_summaries 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_summaries 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_summaries. 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_summaries 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 →