AI agents call feishu_drive_search to retrieve information from Lark Cli without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a read-only search operation on cloud drive files. It queries and returns file metadata but does not create, modify, delete, or execute operations. The blast radius of misuse is limited to potential information disclosure of file listings the user has access to, which is a low-severity risk.
From the tool's definition Tool name 'feishu_drive_search' and description '在云盘中搜索文件（doc/sheet/bitable/file 等），支持类型筛选' (search files in cloud drive, supports type filtering) - this is a search/query operation that retrieves data without modifying it.
Attacks that exploit this kind of access
在云盘中搜索文件（doc/sheet/bitable/file 等），支持类型筛选. It is categorised as a Read tool in the Lark Cli MCP Server, which means it retrieves data without modifying state.
Register the Lark Cli MCP server in PolicyLayer and add a rule for feishu_drive_search: 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 Lark Cli. Nothing to install.
feishu_drive_search 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_drive_search 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_drive_search. 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_drive_search is provided by the Lark Cli MCP server (yoreland/lark-cli-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 →