AI agents use lark_send_message 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 sends messages to Feishu (Lark) chats, which are reversible write operations—messages can be edited or deleted after creation. It modifies the state of chat conversations by adding content, but does not delete, destroy, or execute arbitrary code.
From the tool's definition Tool name 'lark_send_message' and description '向指定的飞书聊天发送文本消息' (send text messages to specified Feishu chats) indicate the tool creates new messages in a messaging platform.
Documented attack patterns abuse exactly the kind of access lark_send_message 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_send_message:
{
"version": "1",
"default": "deny",
"tools": {
"lark_send_message": {
"limits": [
{
"counter": "lark_send_message_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}lark_send_message 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.
向指定的飞书聊天发送文本消息. 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_send_message: 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_send_message 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_send_message 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_send_message. 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_send_message 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.