memory_stash で退避したテキストを復元する。 IDを指定すると、退避されたフル内容を返す。 TTL（デフォルト24時間）を超過したエントリは復元不可。
AI agents call memory_restore 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 tool retrieves/returns previously stashed content by ID without modifying or deleting it. It is a read operation — fetching stored data back into context. The TTL expiry note confirms it is non-destructive. Low severity as it only surfaces already-stored memory content.
From the tool's definition 退避したテキストを復元する。IDを指定すると、退避されたフル内容を返す。(Restores stashed text; returns the full stashed content by ID)
Attacks that exploit this kind of access
memory_stash で退避したテキストを復元する。 IDを指定すると、退避されたフル内容を返す。 TTL（デフォルト24時間）を超過したエントリは復元不可。. 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_restore: 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_restore 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_restore 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_restore. 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_restore 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 →