AI agents use send_message_to_user to create or update resources in Lark MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Lark MCP Server environment.
Sending a message is a reversible write operation that creates new data (the message itself) in Lark. It modifies the message history and notification state for the recipient but does not delete data or execute arbitrary code. Severity is medium because misuse could spam users or send inappropriate messages, but the impact is containable and does not result in permanent data loss or financial harm.
From the tool's definition Tool description states 'Send a message to the user on Lark' — this creates new message data in the Lark system.
Documented attack patterns abuse exactly the kind of access send_message_to_user gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Lark MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for send_message_to_user:
{
"version": "1",
"default": "deny",
"tools": {
"send_message_to_user": {
"limits": [
{
"counter": "send_message_to_user_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} send_message_to_user 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.
Send a message to the user on Lark. It is categorised as a Write tool in the Lark MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Lark MCP Server MCP server in PolicyLayer and add a rule for send_message_to_user: 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 MCP Server. Nothing to install.
send_message_to_user 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 send_message_to_user 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 send_message_to_user. 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.
send_message_to_user is provided by the Lark MCP Server MCP server (junyuan-qi/lark-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Lark MCP Server, 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.
5 Lark MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.