将 Codex 作为 MCP 服务器运行

你可以将 Codex 作为 MCP 服务器运行，并从其他 MCP 客户端连接它（例如，使用 OpenAI Agents SDK MCP 集成构建的智能体）。

若要将 Codex 作为 MCP 服务器启动，可以使用以下命令：

codex mcp-server

你可以使用 Model Context Protocol Inspector 启动 Codex MCP 服务器：

npx @modelcontextprotocol/inspector codex mcp-server

发送 tools/list 请求可查看两个工具：

codex：使用以下提示词和配置覆盖项运行 Codex 会话：

codex-reply：通过提供线程 ID 和提示词继续 Codex 会话。codex-reply 工具接受以下属性：

使用 tools/call 响应中 structuredContent.threadId 的 threadId。审批提示（exec/patch）的 params 有效载荷中也包含 threadId。

响应有效载荷示例：

{
  "structuredContent": {
    "threadId": "019bbb20-bff6-7130-83aa-bf45ab33250e",
    "content": "`ls -lah` (or `ls -alh`) — long listing, includes dotfiles, human-readable sizes."
  },
  "content": [
    {
      "type": "text",
      "text": "`ls -lah` (or `ls -alh`) — long listing, includes dotfiles, human-readable sizes."
    }
  ]
}

请注意，现代 MCP 客户端通常只会将 "structuredContent"（如果存在）报告为工具调用结果，但 Codex MCP 服务器也会返回 "content"，以支持较旧的 MCP 客户端。

创建多智能体工作流

Codex CLI 的能力远不止运行临时任务。通过将 CLI 公开为 Model Context Protocol（MCP）服务器，并使用 OpenAI Agents SDK 对其进行编排，你可以创建确定且可审查的工作流，规模可从单个智能体扩展到完整的软件交付流水线。

本指南将逐步介绍 OpenAI Cookbook 中展示的同一工作流。你将：

• 将 Codex CLI 作为长期运行的 MCP 服务器启动；
• 构建一个专注的单智能体工作流，用于生成可玩的浏览器游戏；以及
• 编排一个包含交接、护栏和完整轨迹的多智能体团队，供你事后审查。

开始之前，请确保你已具备：

• 已在本地安装 Codex CLI，以便使用 codex 命令。
• Python 3.10+ 和 pip。
• 如果要运行上面的 MCP Inspector 示例，需要 Node.js 18+。
• 存储在本地的 OpenAI API key。你可以在 OpenAI 控制面板中创建或管理密钥。

为本指南创建一个工作目录，并将 API key 添加到 .env 文件：

mkdir codex-workflows
cd codex-workflows
printf "OPENAI_API_KEY=sk-..." > .env

安装依赖项

Agents SDK 负责 Codex、交接和轨迹之间的编排。安装最新的 SDK 软件包：

python -m venv .venv
source .venv/bin/activate
pip install --upgrade openai openai-agents python-dotenv

将 Codex CLI 初始化为 MCP 服务器

首先，将 Codex CLI 转换为 Agents SDK 可以调用的 MCP 服务器。该服务器公开两个工具（使用 codex() 启动对话，使用 codex-reply() 继续对话），并让 Codex 在多个智能体轮次间保持运行。

创建名为 codex_mcp.py 的文件并添加以下内容：

import asyncio

from agents import Agent, Runner
from agents.mcp import MCPServerStdio


async def main() -> None:
    async with MCPServerStdio(
        name="Codex CLI",
        params={
            "command": "codex",
            "args": ["mcp-server"],
        },
        client_session_timeout_seconds=360000,
    ) as codex_mcp_server:
        print("Codex MCP server started.")
        # More logic coming in the next sections.
        return


if __name__ == "__main__":
    asyncio.run(main())

运行一次脚本，验证 Codex 能否成功启动：

python codex_mcp.py

脚本会在打印 Codex MCP server started. 后退出。在后续章节中，你将在功能更丰富的工作流内复用同一个 MCP 服务器。

构建单智能体工作流

我们先从一个范围明确的示例开始，使用 Codex MCP 交付一个小型浏览器游戏。该工作流依赖两个智能体：

1. 游戏设计师：编写游戏简介。
2. 游戏开发者：通过调用 Codex MCP 实现游戏。

使用以下代码更新 codex_mcp.py。它会保留上述 MCP 服务器设置，并添加这两个智能体。

import asyncio
import os

from dotenv import load_dotenv

from agents import Agent, Runner, set_default_openai_api
from agents.mcp import MCPServerStdio

load_dotenv(override=True)
set_default_openai_api(os.getenv("OPENAI_API_KEY"))


async def main() -> None:
    async with MCPServerStdio(
        name="Codex CLI",
        params={
            "command": "codex",
            "args": ["mcp-server"],
        },
        client_session_timeout_seconds=360000,
    ) as codex_mcp_server:
        developer_agent = Agent(
            name="Game Developer",
            instructions=(
                "You are an expert in building simple games using basic html + css + javascript with no dependencies. "
                "Save your work in a file called index.html in the current directory. "
                "Always call codex with \"approval-policy\": \"never\" and \"sandbox\": \"workspace-write\"."
            ),
            mcp_servers=[codex_mcp_server],
        )

        designer_agent = Agent(
            name="Game Designer",
            instructions=(
                "You are an indie game connoisseur. Come up with an idea for a single page html + css + javascript game that a developer could build in about 50 lines of code. "
                "Format your request as a 3 sentence design brief for a game developer and call the Game Developer coder with your idea."
            ),
            model="gpt-5",
            handoffs=[developer_agent],
        )

        await Runner.run(designer_agent, "Implement a fun new game!")


if __name__ == "__main__":
    asyncio.run(main())

执行脚本：

python codex_mcp.py

Codex 将读取设计师的简介，创建 index.html 文件，并将完整游戏写入磁盘。在浏览器中打开生成的文件即可游玩。每次运行都会生成不同的设计，具有独特的玩法变化和打磨细节。

扩展为多智能体工作流

现在，将单智能体设置转换为经过编排且可追踪的工作流。系统会添加：

• 项目经理：创建共享需求、协调交接并实施护栏。
• 设计师、前端开发者、服务器开发者和测试人员：各自拥有范围明确的指令和输出文件夹。

创建名为 multi_agent_workflow.py 的新文件：

import asyncio
import os

from dotenv import load_dotenv

from agents import (
    Agent,
    ModelSettings,
    Runner,
    WebSearchTool,
    set_default_openai_api,
)
from agents.extensions.handoff_prompt import RECOMMENDED_PROMPT_PREFIX
from agents.mcp import MCPServerStdio
from openai.types.shared import Reasoning

load_dotenv(override=True)
set_default_openai_api(os.getenv("OPENAI_API_KEY"))


async def main() -> None:
    async with MCPServerStdio(
        name="Codex CLI",
        params={"command": "codex", "args": ["mcp-server"]},
        client_session_timeout_seconds=360000,
    ) as codex_mcp_server:
        designer_agent = Agent(
            name="Designer",
            instructions=(
                f"""{RECOMMENDED_PROMPT_PREFIX}"""
                "You are the Designer.\n"
                "Your only source of truth is AGENT_TASKS.md and REQUIREMENTS.md from the Project Manager.\n"
                "Do not assume anything that is not written there.\n\n"
                "You may use the internet for additional guidance or research."
                "Deliverables (write to /design):\n"
                "- design_spec.md – a single page describing the UI/UX layout, main screens, and key visual notes as requested in AGENT_TASKS.md.\n"
                "- wireframe.md – a simple text or ASCII wireframe if specified.\n\n"
                "Keep the output short and implementation-friendly.\n"
                "When complete, handoff to the Project Manager with transfer_to_project_manager."
                "When creating files, call Codex MCP with {\"approval-policy\":\"never\",\"sandbox\":\"workspace-write\"}."
            ),
            model="gpt-5",
            tools=[WebSearchTool()],
            mcp_servers=[codex_mcp_server],
        )

        frontend_developer_agent = Agent(
            name="Frontend Developer",
            instructions=(
                f"""{RECOMMENDED_PROMPT_PREFIX}"""
                "You are the Frontend Developer.\n"
                "Read AGENT_TASKS.md and design_spec.md. Implement exactly what is described there.\n\n"
                "Deliverables (write to /frontend):\n"
                "- index.html – main page structure\n"
                "- styles.css or inline styles if specified\n"
                "- main.js or game.js if specified\n\n"
                "Follow the Designer’s DOM structure and any integration points given by the Project Manager.\n"
                "Do not add features or branding beyond the provided documents.\n\n"
                "When complete, handoff to the Project Manager with transfer_to_project_manager_agent."
                "When creating files, call Codex MCP with {\"approval-policy\":\"never\",\"sandbox\":\"workspace-write\"}."
            ),
            model="gpt-5",
            mcp_servers=[codex_mcp_server],
        )

        backend_developer_agent = Agent(
            name="Backend Developer",
            instructions=(
                f"""{RECOMMENDED_PROMPT_PREFIX}"""
                "You are the Backend Developer.\n"
                "Read AGENT_TASKS.md and REQUIREMENTS.md. Implement the backend endpoints described there.\n\n"
                "Deliverables (write to /backend):\n"
                "- package.json – include a start script if requested\n"
                "- server.js – implement the API endpoints and logic exactly as specified\n\n"
                "Keep the code as simple and readable as possible. No external database.\n\n"
                "When complete, handoff to the Project Manager with transfer_to_project_manager_agent."
                "When creating files, call Codex MCP with {\"approval-policy\":\"never\",\"sandbox\":\"workspace-write\"}."
            ),
            model="gpt-5",
            mcp_servers=[codex_mcp_server],
        )

        tester_agent = Agent(
            name="Tester",
            instructions=(
                f"""{RECOMMENDED_PROMPT_PREFIX}"""
                "You are the Tester.\n"
                "Read AGENT_TASKS.md and TEST.md. Verify that the outputs of the other roles meet the acceptance criteria.\n\n"
                "Deliverables (write to /tests):\n"
                "- TEST_PLAN.md – bullet list of manual checks or automated steps as requested\n"
                "- test.sh or a simple automated script if specified\n\n"
                "Keep it minimal and easy to run.\n\n"
                "When complete, handoff to the Project Manager with transfer_to_project_manager."
                "When creating files, call Codex MCP with {\"approval-policy\":\"never\",\"sandbox\":\"workspace-write\"}."
            ),
            model="gpt-5",
            mcp_servers=[codex_mcp_server],
        )

        project_manager_agent = Agent(
            name="Project Manager",
            instructions=(
                f"""{RECOMMENDED_PROMPT_PREFIX}"""
                """
                You are the Project Manager.

                Objective:
                Convert the input task list into three project-root files the team will execute against.

                Deliverables (write in project root):
                - REQUIREMENTS.md: concise summary of product goals, target users, key features, and constraints.
                - TEST.md: tasks with [Owner] tags (Designer, Frontend, Backend, Tester) and clear acceptance criteria.
                - AGENT_TASKS.md: one section per role containing:
                  - Project name
                  - Required deliverables (exact file names and purpose)
                  - Key technical notes and constraints

                Process:
                - Resolve ambiguities with minimal, reasonable assumptions. Be specific so each role can act without guessing.
                - Create files using Codex MCP with {"approval-policy":"never","sandbox":"workspace-write"}.
                - Do not create folders. Only create REQUIREMENTS.md, TEST.md, AGENT_TASKS.md.

                Handoffs (gated by required files):
                1) After the three files above are created, hand off to the Designer with transfer_to_designer_agent and include REQUIREMENTS.md and AGENT_TASKS.md.
                2) Wait for the Designer to produce /design/design_spec.md. Verify that file exists before proceeding.
                3) When design_spec.md exists, hand off in parallel to both:
                   - Frontend Developer with transfer_to_frontend_developer_agent (provide design_spec.md, REQUIREMENTS.md, AGENT_TASKS.md).
                   - Backend Developer with transfer_to_backend_developer_agent (provide REQUIREMENTS.md, AGENT_TASKS.md).
                4) Wait for Frontend to produce /frontend/index.html and Backend to produce /backend/server.js. Verify both files exist.
                5) When both exist, hand off to the Tester with transfer_to_tester_agent and provide all prior artifacts and outputs.
                6) Do not advance to the next handoff until the required files for that step are present. If something is missing, request the owning agent to supply it and re-check.

                PM Responsibilities:
                - Coordinate all roles, track file completion, and enforce the above gating checks.
                - Do NOT respond with status updates. Just handoff to the next agent until the project is complete.
                """
            ),
            model="gpt-5",
            model_settings=ModelSettings(
                reasoning=Reasoning(effort="medium"),
            ),
            handoffs=[designer_agent, frontend_developer_agent, backend_developer_agent, tester_agent],
            mcp_servers=[codex_mcp_server],
        )

        designer_agent.handoffs = [project_manager_agent]
        frontend_developer_agent.handoffs = [project_manager_agent]
        backend_developer_agent.handoffs = [project_manager_agent]
        tester_agent.handoffs = [project_manager_agent]

        task_list = """
Goal: Build a tiny browser game to showcase a multi-agent workflow.

High-level requirements:
- Single-screen game called "Bug Busters".
- Player clicks a moving bug to earn points.
- Game ends after 20 seconds and shows final score.
- Optional: submit score to a simple backend and display a top-10 leaderboard.

Roles:
- Designer: create a one-page UI/UX spec and basic wireframe.
- Frontend Developer: implement the page and game logic.
- Backend Developer: implement a minimal API (GET /health, GET/POST /scores).
- Tester: write a quick test plan and a simple script to verify core routes.

Constraints:
- No external database—memory storage is fine.
- Keep everything readable for beginners; no frameworks required.
- All outputs should be small files saved in clearly named folders.
"""

        result = await Runner.run(project_manager_agent, task_list, max_turns=30)
        print(result.final_output)


if __name__ == "__main__":
    asyncio.run(main())

运行脚本并观察生成的文件：

python multi_agent_workflow.py
ls -R

项目经理智能体会写入 REQUIREMENTS.md、TEST.md 和 AGENT_TASKS.md，然后协调设计师、前端、服务器和测试智能体之间的交接。每个智能体都会先在自己的文件夹中写入范围明确的工件，然后再将控制权交还给项目经理。

追踪工作流

Codex 会自动记录轨迹，捕获每个提示词、工具调用和交接。多智能体运行完成后，打开轨迹控制面板查看执行时间线。

高层级轨迹会突出显示项目经理如何在继续推进之前验证交接。点击各个步骤可查看提示词、Codex MCP 调用、写入的文件和执行时长。这些详细信息让你能够轻松审计每次交接，并了解工作流逐轮演变的过程。 这些轨迹无需额外检测机制，即可轻松调试工作流故障、审计智能体行为，并持续衡量性能。