codex-mcp-server
Wraps OpenAI Codex CLI as an MCP server, exposing 8 Codex tools (exec, review, skill list, skill run, status, poll, list jobs, kill) as named tools for use with pi or codex.
README
codex-mcp-server
MCP server（stdio）封裝 OpenAI Codex CLI，讓 pi / Codex 可將 8 個 Codex 工具作為 named tools 呼叫。
來源： C:\Users\hsi67063\.codex\mcp\codex-mcp-server
打包目的： 可攜至其他電腦使用。
目錄結構
codex-mcp-server/
├── index.js # MCP server 本體（已標記需修改路徑）
├── package.json # 依賴：@modelcontextprotocol/sdk + zod
├── README.md # 本檔
├── install.bat # ★ 新電腦安裝腳本（全自動）
└── setup-git.bat # ★ Git 初始化 + Push 腳本
快速安裝（新電腦）
方式一：一鍵安裝（建議）
cd C:\path\to\codex-mcp-server
install.bat
腳本會自動：
- 執行
npm install - 偵測 Codex CLI 路徑，寫入
index.js的CODEX_BIN - 在
pi settings.json中注册mcpServers.codex - 驗證 server 可載入
方式二：手動安裝
# 1. 安裝依賴
cd codex-mcp-server
npm install
# 2. 編輯 index.js，更新 CODEX_BIN 為正確路徑
# 3. 在 pi settings.json 新增：
{
"mcpServers": {
"codex": {
"command": "node",
"args": ["C:/path/to/codex-mcp-server/index.js"]
}
}
}
# 4. 重啟 pi
已注册的工具（8 個）
| 工具 | 模式 | 說明 |
|---|---|---|
codex_exec |
background | 非互動執行 Codex，即時返回 job_id |
codex_review |
sync (5min) | 程式碼審查 |
codex_skill_list |
sync | 列出 Codex skills |
codex_skill_run |
background | 執行指定 skill |
codex_status |
sync (5min) | codex doctor 健康檢查 |
codex_poll |
sync | 查詢背景工作狀態 |
codex_list_jobs |
sync | 列出所有工作 |
codex_kill |
sync | 終止執行中的工作 |
複製到新電腦前需確認
| 項目 | 現有設定 | 新電腦是否需修改 |
|---|---|---|
CODEX_BIN in index.js |
C:/Users/hsi67063/.codex/tools/npm-global/codex.cmd |
是，install.bat 會自動更新 |
DEFAULT_SKILLS_DIR |
C:/Users/hsi67063/.codex/skills |
視需求 |
settings.json 的 args |
絕對路徑 | 是，install.bat 會自動更新 |
Git Push
.\setup-git.bat [remote_url]
範例：
.\setup-git.bat "https://github.com/your_user/codex-mcp-server.git"
若未提供 remote_url，脚本只會初始化 repo 並顯示後續指令。
前置需求
- Node.js 18+
- Codex CLI 已安裝並在 PATH
- pi 或 Codex 已設定
settings.json
疑難排解
Q: npm install 失敗
- 確認網路暢通
- 嘗試：
npm install --legacy-peer-deps
Q: 找不到 Codex CLI
- 手動確認路徑後編輯
index.js中的CODEX_BIN - Codex CLI 常見位置：
C:\Users\<user>\.codex\tools\npm-global\codex.cmdC:\Users\<user>\AppData\Local\OpenAI\Codex\bin\codex.exe
Q: pi 重啟後看不到 codex_ 工具*
- 確認
settings.json中mcpServers.codex區塊已正確寫入 - 檢查 pi 日誌是否有錯誤輸出
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.