向 Word 文档插入 Zotero 原生参考文献字段。
AI agents use insert_bibliography 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 creates and modifies document content by inserting bibliography fields into Word documents. This is a reversible Write operation—the inserted fields can be removed or updated. It does not execute arbitrary code, delete content irreversibly, or involve financial transactions.
From the tool's definition Tool name 'insert_bibliography' and description indicating insertion of Zotero native reference fields into Word documents.
Attacks that exploit this kind of access
向 Word 文档插入 Zotero 原生参考文献字段。. 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 insert_bibliography: 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.
insert_bibliography 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 insert_bibliography 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 insert_bibliography. 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.
insert_bibliography 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 →