设置文档的 Zotero CSL 样式,不立即刷新。
AI agents use set_document_style to create or update resources in Zotero Word — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Zotero Word environment.
This tool modifies document state (the CSL citation style) reversibly. It changes document properties but does not delete, destroy, execute arbitrary code, or move financial resources. The modification is reversible (a style can be changed again), making it Write rather than Destructive.
From the tool's definition The tool description indicates it 'sets' (设置) the document's Zotero CSL style without immediately refreshing. The verb 'set' denotes modification of configuration/metadata within the document.
Attacks that exploit this kind of access
设置文档的 Zotero CSL 样式,不立即刷新。. It is categorised as a Write tool in the Zotero Word MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Zotero Word MCP server in PolicyLayer and add a rule for set_document_style: 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 Zotero Word. Nothing to install.
set_document_style 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 set_document_style 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 set_document_style. 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.
set_document_style is provided by the Zotero Word MCP server (zhangchaokai1/zotero-word-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 →