AI agents invoke gemini_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 triggers external API calls to a large language model service (Google Gemini/Antigravity) with user-supplied prompts, which constitutes execution of arbitrary instructions by a remote system. Misuse could cause the agent to generate harmful code, execute unvetted instructions, or trigger expensive API calls.
From the tool's definition Tool name 'gemini_request_async' and description reference 'Google Antigravity CLI' indicate execution of external model requests asynchronously.
Documented attack patterns abuse exactly the kind of access gemini_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 gemini_request_async:
{
"version": "1",
"default": "deny",
"tools": {
"gemini_request_async": {
"limits": [
{
"counter": "gemini_request_async_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}gemini_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 a Google Antigravity CLI (. 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 gemini_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.
gemini_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 gemini_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 gemini_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.
gemini_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.