What are the requirements to run Codex MCP Wrapper?
Node 22 (specifically version 22.15.1) is required for Codex. The project also uses Node.js, Express, and Python for the MCP server.
@teabranch
基本信息
An MCP server that scales development into controllable agentic, recursive flows, and build a feature from bottom-up
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"agentic-developer-mcp": {
"command": "node",
"args": [
"mcp-server.js"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
Codex MCP Wrapper wraps OpenAI's Codex CLI as an MCP (Model Context Protocol) server, making it accessible through the TeaBranch/open-responses-server middleware. It is designed for developers who want to integrate Codex’s autonomous coding capabilities into MCP-compatible workflows.
Install via Docker (recommended) or manually, then run the MCP server using either stdio or SSE transport. Configure tools in an .agent/mcps.json file and invoke them with parameters such as repository URL and prompt text.
run_codex and clone_and_write_prompt tools.agent/ filesNode 22 (specifically version 22.15.1) is required for Codex. The project also uses Node.js, Express, and Python for the MCP server.
Clone the repository and run `./start.sh` for Docker-based setup, or install dependencies with `npm install`, install Codex CLI globally, and start the MCP server manually.
The MCP server can be run using stdio (default) or SSE transport on a specified port (e.g., `--transport sse --port 8000`).
Two tools: `run_codex` (clones a repo, optionally checks out a branch/folder, and runs Codex with a request) and `clone_and_write_prompt` (reads configuration from `.agent/` files and invokes Codex).
Place an `mcps.json` file under the `.agent/` directory of your repository. Codex loads this configuration automatically to register available MCP tools.
MCP server that lets Claude Code, Cursor or Codex ask you for API keys on a local page and write them to .env. The agent only ever sees key names.
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

The 9apes MCP server lets an AI assistant read the GitHub Actions data 9apes already collects for your organization: runs, jobs, steps, and their durations. Ask it why a build got slower, which jobs take the longest, or

The BetterBugs MCP (Model Context Protocol) enables you to load BetterBugs bug reports (via report links) directly to your preferred AI Agents and developer environments with MCP Client capabilities (such as Cursor, VS C

AI-native payments for tools and APIs. Discover, pay for, execute, and publish monetized APIs directly from your agent, settled per call in USDC over x402, through the Model Context Protocol. payments · finance · x402 ·
评论