AI agents call feishu_search_messages 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 and retrieves existing messages across Feishu/Lark groups. It performs a query operation with no data modification, deletion, or side effects. The action is read-only—it retrieves information without changing state. Severity is low because message search has minimal blast radius and cannot directly cause data loss or financial harm, though it does access user communications.
From the tool's definition Tool name 'feishu_search_messages' and description '跨群搜索飞书消息（用户身份）' (cross-group search Feishu messages as user identity) indicates message querying/retrieval functionality.
Attacks that exploit this kind of access
跨群搜索飞书消息（用户身份）. 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_search_messages: 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_search_messages 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_search_messages 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_search_messages. 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_search_messages 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 →