Send a prompt to OpenAI via Codex exec. Non-interactive, fast startup (no MCP servers loaded), 180s default timeout. Returns clear error on quota limits. For code review, use openai_review instead.
AI agents invoke openai_chat to trigger actions in Claude Concilium. 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.
The tool executes an external process (Codex exec) to send prompts to OpenAI. Unlike a simple API call wrapper, 'exec' implies spawning a subprocess or running a command, which constitutes external execution with effects dependent on the prompt argument. Misuse could lead to unintended external API calls, quota exhaustion, or execution of arbitrary prompts on external AI systems.
From the tool's definition 'Send a prompt to OpenAI via Codex exec' and 'Non-interactive, fast startup' — the word 'exec' indicates execution of an external process/command to invoke OpenAI's Codex
Documented attack patterns abuse exactly the kind of access openai_chat gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Concilium, and nothing reaches the server without passing your rules. This is the rule we recommend for openai_chat:
{
"version": "1",
"default": "deny",
"tools": {
"openai_chat": {
"limits": [
{
"counter": "openai_chat_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}openai_chat 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.
Send a prompt to OpenAI via Codex exec. Non-interactive, fast startup (no MCP servers loaded), 180s default timeout. Returns clear error on quota limits. For code review, use openai_review instead. It is categorised as a Execute tool in the Claude Concilium MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Claude Concilium MCP server in PolicyLayer and add a rule for openai_chat: 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 Claude Concilium. Nothing to install.
openai_chat 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 openai_chat 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 openai_chat. 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.
openai_chat is provided by the Claude Concilium MCP server (spyrae/claude-concilium). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Claude Concilium, 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.
5 Claude Concilium tools catalogued and risk-classified — across an index of 43,000+ MCP servers.