現在のNeuroState・バイアス・ポリシーをスナップショットとして保存する。セッション終了時に呼ぶ。
AI agents use save_snapshot to create or update resources in Memory Engine — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Memory Engine environment.
This tool creates or modifies persistent state data by storing AI agent memory snapshots. While it performs a write operation, it is reversible (not destructive) and has no capability to execute code, move funds, or perform irreversible deletion.
From the tool's definition The tool saves ('保存する') the current NeuroState, biases, and policies as a snapshot. This is a persistent write operation that creates or modifies data (snapshot creation) but is reversible—snapshots can be overwritten or deleted.
Attacks that exploit this kind of access
現在のNeuroState・バイアス・ポリシーをスナップショットとして保存する。セッション終了時に呼ぶ。. It is categorised as a Write tool in the Memory Engine MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Memory Engine MCP server in PolicyLayer and add a rule for save_snapshot: 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.
save_snapshot is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the save_snapshot 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 save_snapshot. 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.
save_snapshot 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 →