AI agents use lark_set_primary_chat to create or update resources in Feishu Enhance — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Feishu Enhance environment.
This tool modifies system state by changing the primary chat configuration, which affects which messages are monitored. This is a reversible write operation (the configuration can be changed again) rather than destructive deletion. While it doesn't create new data objects, it updates an important system setting.
From the tool's definition Tool name 'lark_set_primary_chat' and description '设置主监听群聊ID' (set primary listening group chat ID) indicates modifying a configuration setting that designates which chat channel is monitored as primary.
Documented attack patterns abuse exactly the kind of access lark_set_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_set_primary_chat:
{
"version": "1",
"default": "deny",
"tools": {
"lark_set_primary_chat": {
"limits": [
{
"counter": "lark_set_primary_chat_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}lark_set_primary_chat stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
设置主监听群聊ID. It is categorised as a Write tool in the Feishu Enhance MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Feishu Enhance MCP server in PolicyLayer and add a rule for lark_set_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_set_primary_chat is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the lark_set_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_set_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_set_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.