將指定對話的所有記憶備份到文件。支持導出短期和長期記憶,包含完整的元數據和時間戳。
AI agents use backup_memories to create or update resources in Memory MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Memory MCP Server environment.
This tool writes memory data to a backup file. It is a data export/write operation — it creates a new file containing memories. It does not delete or modify existing data, so it is not Destructive. Since it creates/writes a backup artifact, Write is the most appropriate category. Misuse could expose sensitive conversation memories, hence medium severity.
From the tool's definition 備份到文件 (backup to file), 導出短期和長期記憶 (export short-term and long-term memories), 包含完整的元數據和時間戳 (including complete metadata and timestamps)
Attacks that exploit this kind of access
將指定對話的所有記憶備份到文件。支持導出短期和長期記憶,包含完整的元數據和時間戳。. It is categorised as a Write tool in the Memory MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Memory MCP Server MCP server in PolicyLayer and add a rule for backup_memories: 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 MCP Server. Nothing to install.
backup_memories 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 backup_memories 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 backup_memories. 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.
backup_memories is provided by the Memory MCP Server MCP server (win10ogod/memory-mcp-server). 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 →