列出可用的備份文件
AI agents call list_backups to retrieve information from Memory MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a straightforward enumeration of backup files, which is a read-only operation that retrieves data without creating, modifying, deleting, or executing anything. Even in the context of a memory management system, listing backups is non-destructive information retrieval. The low severity reflects that knowing what backups exist poses minimal risk unless combined with other tools like delete_backup.
From the tool's definition Tool name is 'list_backups' and description translates to 'List available backup files'. This retrieves or queries information about existing backups with no side effects or modifications.
Attacks that exploit this kind of access
列出可用的備份文件. It is categorised as a Read tool in the Memory MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Memory MCP Server MCP server in PolicyLayer and add a rule for list_backups: 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.
list_backups 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_backups 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_backups. 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_backups 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 →