Start a Mistral Vibe CLI request as a durable background job. Poll with llm_job_status, collect with llm_job_result.
AI agents invoke mistral_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 initiates execution of arbitrary Mistral CLI commands asynchronously. While the tool itself does not directly delete or move money, it invokes an external CLI that could perform such actions based on attacker-controlled input. The high severity reflects that a compromised or manipulated request could execute harmful operations (shell commands, API calls, data exfiltration) without direct visibility.
From the tool's definition Tool description states it 'Start[s] a Mistral Vibe CLI request as a durable background job.' The phrase 'CLI request' indicates execution of commands through a language model CLI interface.
Documented attack patterns abuse exactly the kind of access mistral_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 mistral_request_async:
{
"version": "1",
"default": "deny",
"tools": {
"mistral_request_async": {
"limits": [
{
"counter": "mistral_request_async_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}mistral_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 Mistral Vibe 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 mistral_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.
mistral_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 mistral_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 mistral_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.
mistral_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.