Start an xAI Grok CLI request as a durable background job. Poll with llm_job_status, collect with llm_job_result.
AI agents invoke grok_request_async to trigger actions in LLM CLI Gateway. 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 executes arbitrary Grok CLI commands asynchronously. Although it does not directly read/write/delete data itself, it triggers external command execution on another LLM service, making it an Execute-class risk. The async nature and durable job queueing increase the blast radius—a compromised agent could queue numerous expensive or harmful commands.
From the tool's definition Starts an xAI Grok CLI request as a durable background job; 'CLI request' and 'background job' indicate command execution whose effects depend on arguments provided by an AI agent.
Documented attack patterns abuse exactly the kind of access grok_request_async gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and LLM CLI Gateway, and nothing reaches the server without passing your rules. This is the rule we recommend for grok_request_async:
{
"version": "1",
"default": "deny",
"tools": {
"grok_request_async": {
"limits": [
{
"counter": "grok_request_async_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}grok_request_async 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.
Start an xAI Grok CLI request as a durable background job. Poll with llm_job_status, collect with llm_job_result. It is categorised as a Execute tool in the LLM CLI Gateway MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the LLM CLI Gateway MCP server in PolicyLayer and add a rule for grok_request_async: 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 LLM CLI Gateway. Nothing to install.
grok_request_async 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 grok_request_async 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 grok_request_async. 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.
grok_request_async is provided by the LLM CLI Gateway MCP server (llm-cli-gateway). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from LLM CLI Gateway, 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.
46 LLM CLI Gateway tools catalogued and risk-classified — across an index of 43,000+ MCP servers.