AI agents call lark_get_primary_chat to retrieve information from Feishu Enhance without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves the ID of a primary monitored chat group—a pure read operation with no side effects. It queries existing configuration state and returns an identifier. The blast radius is minimal: knowing a chat ID does not by itself enable unauthorized actions on that chat. This is consistent with the sibling tool 'lark_get_chat_info' and other read tools in the server (lark_get_messages, lark_get_chat_list).
From the tool's definition The tool name 'lark_get_primary_chat' and description '获取当前主监听群聊ID' (get current primary monitored group chat ID) indicates a retrieval operation that fetches an identifier without modifying data or triggering external operations.
Documented attack patterns abuse exactly the kind of access lark_get_primary_chat gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Feishu Enhance, and nothing reaches the server without passing your rules. This is the rule we recommend for lark_get_primary_chat:
{
"version": "1",
"default": "deny",
"tools": {
"lark_get_primary_chat": {}
}
}lark_get_primary_chat is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
获取当前主监听群聊ID. It is categorised as a Read tool in the Feishu Enhance MCP Server, which means it retrieves data without modifying state.
Register the Feishu Enhance MCP server in PolicyLayer and add a rule for lark_get_primary_chat: 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 Enhance. Nothing to install.
lark_get_primary_chat 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 lark_get_primary_chat 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 lark_get_primary_chat. 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.
lark_get_primary_chat is provided by the Feishu Enhance MCP server (jiaxinghit/feishu-enhance-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Feishu Enhance, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
24 Feishu Enhance tools catalogued and risk-classified — across an index of 43,000+ MCP servers.