Fork an existing Codex session into a new branch (codex fork <ID|--last>) and run a prompt against the fork without mutating the original.
AI agents invoke codex_fork_session 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.
The tool invokes execution of user-supplied prompts against a Codex session, which is an external operation whose effects cannot be predicted or controlled without understanding the prompt. While it avoids mutating the original session (mitigating some risk), the ability to execute arbitrary prompts in a forked context without restriction places it in the Execute category.
From the tool's definition Tool allows running arbitrary prompts against a forked Codex session ('run a prompt against the fork'). This executes code or commands in an external LLM/CLI context with side effects dependent on the prompt content.
Documented attack patterns abuse exactly the kind of access codex_fork_session 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_fork_session:
{
"version": "1",
"default": "deny",
"tools": {
"codex_fork_session": {
"limits": [
{
"counter": "codex_fork_session_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}codex_fork_session 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.
Fork an existing Codex session into a new branch (codex fork <ID|--last>) and run a prompt against the fork without mutating the original. 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_fork_session: 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_fork_session 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_fork_session 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_fork_session. 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_fork_session 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.