AI agents call feishu_doc_read to retrieve information from Feishu without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries document content without side effects. It performs a read operation—fetching data from Feishu documents and returning it as text. No creation, modification, execution, destruction, or financial action is performed. This is a straightforward data retrieval operation with minimal risk if misused by an AI agent.
From the tool's definition Tool name is 'feishu_doc_read' and description explicitly states '读取飞书文档内容' (read Feishu document content), returning raw text in markdown format with no modification or deletion semantics.
Attacks that exploit this kind of access
读取飞书文档内容，返回 raw text（markdown 格式）. It is categorised as a Read tool in the Feishu MCP Server, which means it retrieves data without modifying state.
Register the Feishu MCP server in PolicyLayer and add a rule for feishu_doc_read: 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_read is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the feishu_doc_read 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_read. 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_read 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 →