AI agents use lark_reply_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 a reply to an existing Feishu message. It creates new message content in a conversation, which is a reversible write operation (messages can be deleted or retracted). The blast radius is medium since a misused AI agent could send unintended replies to business communications.
From the tool's definition 回复指定的飞书消息 (Reply to a specified Feishu message)
Documented attack patterns abuse exactly the kind of access lark_reply_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_reply_message:
{
"version": "1",
"default": "deny",
"tools": {
"lark_reply_message": {
"limits": [
{
"counter": "lark_reply_message_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}lark_reply_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.
回复指定的飞书消息. 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_reply_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_reply_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_reply_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_reply_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_reply_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.