memory_search で取得したIDを指定して、メモリのフル詳細を取得する。 複数IDを一括指定可能。必要なものだけ取得してトークンを節約すること。
AI agents call memory_get_detail to retrieve information from Wasurenagusa without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Read operation—it retrieves detailed memory data based on provided IDs. However, the severity is raised to 'medium' rather than 'low' because: (1) the server's core purpose involves 'persistent memory for AI assistants' that stores 'project-specific rules, decisions, and configurations'—sensitive operational context; (2) an agent with unrestricted access to memory_get_detail could enumerate and exfiltrate…
From the tool's definition Tool description translates to 'Specify the ID obtained with memory_search to get the full details of the memory. Multiple IDs can be specified at once.
Attacks that exploit this kind of access
memory_search で取得したIDを指定して、メモリのフル詳細を取得する。 複数IDを一括指定可能。必要なものだけ取得してトークンを節約すること。. It is categorised as a Read tool in the Wasurenagusa MCP Server, which means it retrieves data without modifying state.
Register the Wasurenagusa MCP server in PolicyLayer and add a rule for memory_get_detail: 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 Wasurenagusa. Nothing to install.
memory_get_detail 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 memory_get_detail 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 memory_get_detail. 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.
memory_get_detail is provided by the Wasurenagusa MCP server (tsutushi0628/wasurenagusa-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 →