AI agents call feishu_base_record_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.
This tool searches for and retrieves records from a database table. It performs a query operation that returns data without creating, modifying, deleting, or executing side effects. The action is read-only and has minimal blast radius if misused—worst case, an AI agent queries data it shouldn't access, but the data itself remains intact.
From the tool's definition Tool name 'feishu_base_record_search' and description '在多维表格数据表中检索记录' (search/retrieve records in multidimensional table datasets) indicate a search/retrieval operation with no modification or deletion.
Attacks that exploit this kind of access
在多维表格数据表中检索记录. 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_base_record_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_base_record_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_base_record_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_base_record_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_base_record_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 →