删除 Word 文档中的书签.
AI agents call delete_word_bookmark to permanently remove resources in Office MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool irreversibly deletes bookmarks from Word documents. While bookmarks are metadata rather than primary content, their deletion cannot be undone and may break document references, cross-references, or navigation structures that depend on those bookmarks. This qualifies as Destructive because the operation is permanent and cannot be easily reversed.
From the tool's definition Tool name 'delete_word_bookmark' and description '删除 Word 文档中的书签' (Delete bookmarks in Word documents) — explicit deletion operation on document bookmarks.
Attacks that exploit this kind of access
删除 Word 文档中的书签. It is categorised as a Destructive tool in the Office MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Office MCP Server MCP server in PolicyLayer and add a rule for delete_word_bookmark: 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 Office MCP Server. Nothing to install.
delete_word_bookmark 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 delete_word_bookmark 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 delete_word_bookmark. 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.
delete_word_bookmark is provided by the Office MCP Server MCP server (walkingzzzy/office-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 →