~/.codex/config.toml, or from .codex/config.toml in a project you have marked as trusted. It starts each server itself, outside its sandbox, so the browser works whatever sandbox_mode is.
Add the server
1
Download the browser
2
Add the server
~/.codex/config.toml. Put --env KEY=VALUE options before --.3
Set timeouts and approval
Open
~/.codex/config.toml and complete the entry:~/.codex/config.toml
examples/agents/mcp/codex.config.toml. To approve only some tools, leave default_tools_approval_mode at its default and set approval_mode = "approve" per tool under [mcp_servers.apostate.tools.<tool>].
Run a task
-c overrides:
Scripts and skills
Codex loads skills from.agents/skills/<name>/SKILL.md in the project (from the working directory up to the repository root) and from ~/.agents/skills/. The Apostate skill works there unchanged:
workspace-write mode the network is off, and a browser started from a sandboxed command crashes: on macOS with MachPortRendezvousServer ... Permission denied, on Linux with SIGTRAP. For script work, run Codex with --sandbox danger-full-access in a disposable environment, or use the MCP server, which Codex starts outside the sandbox.
AGENTS.md
Codex readsAGENTS.md from ~/.codex/ and from each directory between the repository root and the working directory. A short section keeps browsing consistent:
AGENTS.md