AI agents invoke sleep to trigger actions in MCPHub. 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.
The tool executes a timed wait/sleep operation on the system. While it doesn't modify data, it actively triggers a blocking execution behavior that can affect agent workflows (e.g., delay operations, enable polling loops). This is an execution-class action rather than a pure read. Severity is low since misuse (e.g., excessive sleep durations) primarily causes delays rather than data loss or financial harm.
From the tool's definition 等待指定时长。可以实现间隔轮询、等待等任务。 (Wait for a specified duration. Can implement interval polling, waiting tasks.)
Attacks that exploit this kind of access
等待指定时长。可以实现间隔轮询、等待等任务。. It is categorised as a Execute tool in the MCPHub MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCPHub MCP server in PolicyLayer and add a rule for sleep: 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 MCPHub. Nothing to install.
sleep 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 sleep 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 sleep. 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.
sleep is provided by the MCPHub MCP server (jayden-dong/mcphub). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →