One brain, many arms. Spawn multiple specialized Codex agents as MCP servers via the OpenAI Codex SDK. Each instance gets its own model, sandbox, effort, and personality.
Overview
Codex Octopus
One brain, many arms.
An MCP server that wraps the OpenAI Codex SDK, letting you run multiple specialized Codex agents — each with its own model, sandbox, effort, and personality — from any MCP client.
Why
Codex is powerful. But one instance does everything the same way. Sometimes you want a strict code reviewer in read-only sandbox. A test writer with workspace-write access. A cheap quick helper on minimal effort. A deep thinker on xhigh.
Codex Octopus lets you spin up as many of these as you need. Same binary, different configurations.
Quick Start
{
"mcpServers": {
"codex": {
"command": "npx",
"args": ["codex-octopus"],
"env": {
"CODEX_SANDBOX_MODE": "workspace-write",
"CODEX_APPROVAL_POLICY": "never"
}
}
}
}
Key Features
- Multi-instance — run several agents with different configs simultaneously
- Per-invocation overrides — model, sandbox, effort, approval policy, cwd
- Session continuity — follow up on previous conversations via
_replytool - Factory wizard — generate
.mcp.jsonconfigs interactively - Security narrowing — sandbox and approval can only tighten per invocation
Links
Server Config
{
"mcpServers": {
"codex": {
"command": "npx",
"args": [
"codex-octopus"
],
"env": {
"CODEX_SANDBOX_MODE": "workspace-write",
"CODEX_APPROVAL_POLICY": "never"
}
}
}
}