AI agents invoke lark_create_async_task to trigger actions in Feishu Enhance. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool creates and triggers asynchronous tasks that run operations. 'Long-running operations' implies execution of processes with potentially wide-ranging effects depending on what the task does. Since the description is vague about what operations are triggered, Execute is appropriate as it clearly initiates external operations.
From the tool's definition 创建异步任务，用于长时间运行的操作 (Create async task for long-running operations)
Documented attack patterns abuse exactly the kind of access lark_create_async_task 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_create_async_task:
{
"version": "1",
"default": "deny",
"tools": {
"lark_create_async_task": {
"limits": [
{
"counter": "lark_create_async_task_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}lark_create_async_task stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
创建异步任务，用于长时间运行的操作. It is categorised as a Execute tool in the Feishu Enhance MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Feishu Enhance MCP server in PolicyLayer and add a rule for lark_create_async_task: 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_create_async_task is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the lark_create_async_task 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_create_async_task. 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_create_async_task 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.