AI agents use feishu_doc_write to create or update resources in Feishu — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Feishu environment.
The tool creates or modifies data reversibly by writing markdown content to Feishu documents. Although it clears the document before writing, the operation is reversible (documents can be restored or re-written). This falls squarely into the Write category.
From the tool's definition Tool description states '写入内容到飞书文档。会先清空文档再写入' (write content to Feishu document; clears document first before writing). This is explicitly a write operation that modifies document content.
Attacks that exploit this kind of access
写入内容到飞书文档。会先清空文档再写入(用 markdown 内容)。. It is categorised as a Write tool in the Feishu MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Feishu MCP server in PolicyLayer and add a rule for feishu_doc_write: 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 Feishu. Nothing to install.
feishu_doc_write 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 feishu_doc_write 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 feishu_doc_write. 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.
feishu_doc_write is provided by the Feishu MCP server (zlplzp123wyt/feishu-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 →