AI agents invoke poll to trigger actions in Async Bash. 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.
Given the server's purpose of managing async bash commands and sibling tools 'spawn' (likely starts a process) and 'list_processes' (lists processes), 'poll' most likely retrieves the status or output of a running process. This is primarily a Read operation, but since it operates within an Execute-class server managing shell commands, and could potentially interact with or advance process state, Execute is assigned.
From the tool's definition Tool description is empty; classification inferred from server context: 'An MCP server for spawning and managing bash commands asynchronously.
Documented attack patterns abuse exactly the kind of access poll gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Async Bash, and nothing reaches the server without passing your rules. This is the rule we recommend for poll:
{
"version": "1",
"default": "deny",
"tools": {
"poll": {
"limits": [
{
"counter": "poll_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}poll 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.
poll. It is categorised as a Execute tool in the Async Bash MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Async Bash MCP server in PolicyLayer and add a rule for poll: 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 Async Bash. Nothing to install.
poll 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 poll 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 poll. 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.
poll is provided by the Async Bash MCP server (xhuw/async-bash-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Async Bash, 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.
3 Async Bash tools catalogued and risk-classified — across an index of 43,000+ MCP servers.