Run an OpenAI Codex CLI request synchronously (when async jobs are enabled, auto-defers to a pollable job past the sync deadline; otherwise runs to completion). Requires exactly one of prompt or promptParts.
AI agents invoke codex_request 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 code generation/execution via the OpenAI Codex API based on user-supplied prompts. The severity is high because: (1) Codex can generate and potentially execute arbitrary code; (2) prompt injection attacks could lead to unintended code generation or execution; (3) the tool's output directly influences downstream operations.
From the tool's definition Tool runs an 'OpenAI Codex CLI request' with a prompt, which executes code generation or execution through an external LLM service. The description indicates it processes prompts and can defer to async jobs, confirming active execution of operations.
Documented attack patterns abuse exactly the kind of access codex_request 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 codex_request:
{
"version": "1",
"default": "deny",
"tools": {
"codex_request": {
"limits": [
{
"counter": "codex_request_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}codex_request 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.
Run an OpenAI Codex CLI request synchronously (when async jobs are enabled, auto-defers to a pollable job past the sync deadline; otherwise runs to completion). Requires exactly one of prompt or promptParts. 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 codex_request: 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.
codex_request 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 codex_request 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 codex_request. 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.
codex_request 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.