使用 Codex 与 Agents SDK | ChatGPT Learn

来源: https://developers.openai.com/codex/guides/agents-sdk 抓取时间: 2026-07-21 16:26:46

将 Codex 作为 MCP 服务器运行

您可以将 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）。

要将 Codex 作为 MCP 服务器启动，您可以使用以下命令：

codex mcp-server

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

npx @modelcontextprotocol/inspector codex mcp-server

发送 tools/list 请求查看两个工具：

codex ：使用以下提示和配置覆盖运行 Codex 会话：

属性	类型	描述
`prompt`（必需）	`string`	启动 Codex 对话的初始用户提示。
`approval-policy`	`string`	模型生成的 shell 命令的批准策略：`untrusted`、`on-request` 和 `never`。
`base-instructions`	`string`	替代默认指令的指令集。
`compact-prompt`	`string`	压缩对话时使用的提示。
`config`	`object`	覆盖 `$CODEX_HOME/config.toml` 中内容的单个配置设置。
`cwd`	`string`	会话的工作目录。如果是相对路径，则相对于服务器进程的当前目录解析。
`developer-instructions`	`string`	作为开发者角色消息注入的开发者指令。
`model`	`string`	模型名称的可选覆盖（例如，`gpt-5.4`）。
`sandbox`	`string`	沙箱模式：`read-only`、`workspace-write` 或 `danger-full-access`。

codex-reply ：通过提供线程 ID 和提示继续 Codex 会话。codex-reply 工具使用以下属性：

属性	类型	描述
`prompt`（必需）	string	继续 Codex 对话的下一个用户提示。
`threadId`（必需）	string	要继续的线程的 ID。
`conversationId`（已弃用）	string	`threadId` 的已弃用别名（为兼容性保留）。

使用 tools/call 响应中 structuredContent.threadId 的 threadId。批准提示（exec/patch）也在其 params 有效负载中包含 threadId。

示例响应有效负载：

{
  "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 客户端通常只报告 "structuredContent" 作为工具调用的结果（如果存在），尽管 Codex MCP 服务器也返回 "content" 以便旧版 MCP 客户端受益。

创建多智能体工作流程

Codex CLI 远不止运行临时任务。通过将 CLI 作为 Model Context Protocol (MCP) 服务器公开并使用 OpenAI Agents SDK 对其进行编排，您可以创建确定的、可审核的工作流程，从单个智能体扩展到完整的软件交付管道。

本指南介绍了与 OpenAI Cookbook 中展示的相同工作流程。您将：

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程，生成可在浏览器中玩的游戏，以及
编排一个多智能体团队，包含交接、护栏和您可以事后审核的完整追踪。

开始之前，请确保您已：

在本地安装了 Codex CLI，以便 codex 命令可用。
带有 pip 的 Python 3.10+。
如果要运行上面的 MCP Inspector 示例，则需要 Node.js 18+。
本地存储的 OpenAI API 密钥。您可以在 OpenAI 仪表板中创建或管理密钥。

为指南创建一个工作目录，并将您的 API 密钥添加到 .env 文件中：

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

安装依赖

Agents SDK 处理跨 Codex 的编排、交接和追踪。安装最新的 SDK 包：

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

激活虚拟环境可将 SDK 依赖项与系统的其余部分隔离。

将 Codex CLI 初始化为 MCP 服务器

首先将 Codex CLI 转变为 Agents SDK 可以调用的 MCP 服务器。该服务器公开两个工具（codex() 用于开始对话，codex-reply() 用于继续对话），并在多个智能体回合中保持 Codex 活动。

创建一个名为 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())

运行脚本一次以验证 Codex 成功启动：

python codex_mcp.py

脚本在打印 Codex MCP server started. 后退出。在接下来的章节中，您将在更丰富的工作流程中重用相同的 MCP 服务器。

构建单智能体工作流程

让我们从一个使用 Codex MCP 交付小型浏览器游戏的范围明确的示例开始。该工作流程依赖于两个智能体：

游戏设计师：编写游戏简介。
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。它保留了上面的 MCP 服务器设置并添加了两个智能体。

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 将阅读设计师的简介，创建一个 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以玩游戏。每次运行都会产生不同的设计，具有独特的游戏风格扭曲和润色。

扩展到多智能体工作流程

现在将单智能体设置转变为编排的、可追踪的工作流程。系统添加：

项目经理：创建共享需求，协调交接，并强制执行护栏。
设计师、前端开发者、服务器开发者 和 测试员：每个都有范围明确的指令和输出文件夹。

创建一个名为 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、服务器和测试员智能体之间的交接。每个智能体在将控制权交还给项目经理之前，将范围明确的工件写入其自己的文件夹。

追踪工作流程

Codex 自动记录追踪，捕获每个提示、工具调用和交接。多智能体运行完成后，打开 Traces 仪表板以检查执行时间线。

高级追踪突出显示了项目经理如何在继续之前验证交接。点击进入各个步骤以查看提示、Codex MCP 调用、写入的文件和执行持续时间。这些详细信息使审核每个交接和理解工作流程如何逐回合演变变得简单明了。这些追踪使调试工作流程问题、审核智能体行为和随时间衡量性能变得简单，无需额外的检测。

使用 Codex 与 Agents SDK | ChatGPT Learn

使用 Codex 与 Agents SDK | ChatGPT Learn

将 Codex 作为 MCP 服务器运行

创建多智能体工作流程

安装依赖

将 Codex CLI 初始化为 MCP 服务器

构建单智能体工作流程

扩展到多智能体工作流程

追踪工作流程

评论 (0)