清除指定的内存内容
AI agents call clear_memory to permanently remove resources in Word Document Reader MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Clearing memory content is an irreversible operation — once in-memory data is purged, it cannot be recovered without re-reading the original documents. This aligns with Destructive. However, since it affects only cached/in-memory data (not the source documents themselves), the blast radius is medium rather than high.
From the tool's definition Tool name 'clear_memory' and description '清除指定的内存内容' (Clear specified memory content). The word '清除' means 'clear/purge' in Chinese.
Attacks that exploit this kind of access
清除指定的内存内容. It is categorised as a Destructive tool in the Word Document Reader MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Word Document Reader MCP Server MCP server in PolicyLayer and add a rule for clear_memory: 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 Word Document Reader MCP Server. Nothing to install.
clear_memory is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the clear_memory 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 clear_memory. 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.
clear_memory is provided by the Word Document Reader MCP Server MCP server (little2512/word-doc-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 →