セッションの要約を保存する。スナップショットも同時に保存できる。セッション終了時に呼ぶ。
AI agents use summarize_session 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.
The tool creates/stores data (session summary and optional snapshot) in the memory engine. This is a Write operation since it persists new records without irreversibly destroying existing data. Severity is medium because an AI agent misusing this tool could corrupt session history or inject false memories, affecting future agent behavior across sessions.
From the tool's definition 「セッションの要約を保存する。スナップショットも同時に保存できる。」— the tool saves/stores a session summary and optionally a snapshot, which are reversible write operations.
Attacks that exploit this kind of access
セッションの要約を保存する。スナップショットも同時に保存できる。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 summarize_session: 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.
summarize_session 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 summarize_session 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 summarize_session. 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.
summarize_session 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 →