保存済みスナップショットの一覧を返す。
AI agents call list_snapshots 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 or queries existing snapshot metadata without side effects. It is a read-only operation that lists previously saved snapshots for the AI agent's memory system, analogous to a directory or inventory operation. No data is created, modified, deleted, or executed—only queried.
From the tool's definition Tool name 'list_snapshots' and description indicating it 'returns a list of saved snapshots' (from Japanese: 保存済みスナップショットの一覧を返す = 'returns a list of saved snapshots') performs only data retrieval with no modification or deletion.
Attacks that exploit this kind of access
保存済みスナップショットの一覧を返す。. 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 list_snapshots: 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.
list_snapshots 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 list_snapshots 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 list_snapshots. 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.
list_snapshots 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 →