{
  "markdown": "# Codex Delegate\n\n**Stop burning your frontier agent's limits on boilerplate.**\n\nDelegate implementation to the **OpenAI Codex CLI** — your agent writes the brief and reviews the diff.\n\n[![npm version](https://img.shields.io/npm/v/codex-delegate-mcp)](https://www.npmjs.com/package/codex-delegate-mcp)\n[![npm downloads](https://img.shields.io/npm/dt/codex-delegate-mcp)](https://www.npmjs.com/package/codex-delegate-mcp)\n[![MCP Registry](https://img.shields.io/badge/MCP%20Registry-listed-blue)](https://registry.modelcontextprotocol.io/v0/servers?search=codex-delegate)\n[![codex-delegate-mcp MCP server](https://glama.ai/mcp/servers/andreilungeanu/codex-delegate-mcp/badges/score.svg)](https://glama.ai/mcp/servers/andreilungeanu/codex-delegate-mcp)\n[![node](https://img.shields.io/node/v/codex-delegate-mcp)](https://nodejs.org)\n[![license: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)\n[![tests](https://github.com/andreilungeanu/codex-delegate-mcp/actions/workflows/test.yml/badge.svg)](https://github.com/andreilungeanu/codex-delegate-mcp/actions/workflows/test.yml)\n\n<img src=\"assets/logo-light.png\" alt=\"Codex Delegate logo\" width=\"150\" align=\"left\" hspace=\"15\">\n\nUse your best coding agent where its judgment matters most: understanding the task, shaping the plan, and reviewing the result.\n\nCodex Delegate is the MCP bridge that lets Claude Code, Cursor, Copilot — or any MCP client — hand implementation to the **OpenAI Codex CLI**, then get a clean, structured result back for review.\n\n<br clear=\"left\">\n\n![A terminal recording of Claude Code delegating to Codex: a health check confirms the Codex CLI, auth and model catalog; an ask-mode run diagnoses why the demo repo prints \"today 0\", naming commitDay() bucketing by UTC while cellDay() labels by local time, with line numbers; one sentence then fans out to two Codex models at once — one editing the repo, one researching in a separate directory — and the fix lands with tests passing and the footer reading today 4, current streak 23, longest streak 23; finally Codex reviews its own diff and reports three findings](assets/demo.gif)\n\n## 🧠 Frontier quality, kept\n\nYour assistant does what frontier models are actually for: understands the task, writes a precise brief, reviews the finished diff. Codex holds its own as the implementer — guided and checked by a smarter orchestrator. The result reads like frontier work, because a frontier model planned it and signed off on it.\n\n## ⚡ Done faster\n\nCodex tears through multi-file edits while a frontier chat model would still be streaming the first file. You delegate, keep working with your assistant, and the diff shows up done.\n\n## 🔋 Your limits stop being the bottleneck\n\nDelegated work runs on the **OpenAI Codex CLI** and its own usage — separate from your orchestrator's chat quota, though the Codex side still bills its own way. Your Claude, Cursor, or Copilot subscription spends tokens on the brief and the review; Codex does the grinding. On API? That's the per-token grind moved off your main bill.\n\n# \n\n![You and your agent understand the task, write the brief and review the diff; the MCP delegate tool hands that brief to the OpenAI Codex CLI, which implements it and edits your workspace; one compact JSON result comes back with what changed, which files, and the thread id](assets/flow.png)\n\n![A delegate result: one compact JSON block with the final answer, status, thread and delegation ids, workspace, Codex CLI version, cumulative thread token usage, and the files the edit tools reported changing](assets/result-json.png)\n\n## Features\n\n- 📦 **One result you can review** — a compact JSON block: the final answer, `status`, the files Codex's edit tools reported changing, cumulative thread token counts, and the `threadId` to continue from. Fields that carry no signal are omitted.\n- 📋 **Plan first, then build it on the same thread** — `plan` returns schema-validated steps for you to approve, and `agent` implements them. `ask` answers questions. `review` runs Codex's own reviewer over uncommitted work, a base branch, or a single commit.\n- 🧵 **Resume** — continue a Codex thread with `resumeThreadId`. `resumed: false` tells you the context did not carry over.\n- 🧑‍🤝‍🧑 **Run several, cancel cleanly** — the same question across models, or independent workers on independent directories. `cancel` waits for the exit and warns when a process outlives the kill deadline.\n- 🤝 **One-command install** — Claude Code and GitHub Copilot CLI take it as a plugin, with a skill that teaches your agent how to delegate well. Cursor, VS Code, JetBrains, Windsurf and Visual Studio add the stdio server in settings.\n- 🩺 **`doctor`** — tells you exactly what's missing if setup isn't right.\n\n## Install\n\nYou need [Node.js 20+](https://nodejs.org/) and the [OpenAI Codex CLI](https://github.com/openai/codex), already logged in (`codex login`).\n\n### Claude Code\n\n```shell\n/plugin marketplace add andreilungeanu/codex-delegate-mcp\n/plugin install codex-delegate@codex-delegate-mcp\n```\n\nThen just ask:\n\n> Delegate to Codex: migrate src/api from callbacks to async/await and update the tests, then walk me through what changed.\n\nThat's the whole loop — Claude writes the brief, Codex grinds through the files, Claude walks you through the diff.\n\n### Cursor\n\nAdd an MCP server in **Cursor Settings → MCP** (or project `.cursor/mcp.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"codex-delegate\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"codex-delegate-mcp\"]\n    }\n  }\n}\n```\n\nThen ask Cursor to delegate implementation to Codex the same way.\n\n### GitHub Copilot CLI\n\n```shell\ncopilot plugin install andreilungeanu/codex-delegate-mcp\n```\n\n### More clients\n\n<details>\n<summary><strong>VS Code</strong> — one-click install, or <code>.vscode/mcp.json</code></summary>\n\n[![Install in VS Code](https://img.shields.io/badge/VS_Code-Install_server-0098FF?style=flat-square&logo=visualstudiocode&logoColor=white)](https://vscode.dev/redirect/mcp/install?name=codex-delegate&config=%7B%22type%22%3A%22stdio%22%2C%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22codex-delegate-mcp%22%5D%7D)\n[![Install in VS Code Insiders](https://img.shields.io/badge/VS_Code_Insiders-Install_server-24bfa5?style=flat-square&logo=visualstudiocode&logoColor=white)](https://insiders.vscode.dev/redirect/mcp/install?name=codex-delegate&config=%7B%22type%22%3A%22stdio%22%2C%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22codex-delegate-mcp%22%5D%7D&quality=insiders)\n\n```json\n{\n  \"servers\": {\n    \"codex-delegate\": {\n      \"type\": \"stdio\",\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"codex-delegate-mcp\"]\n    }\n  }\n}\n```\n\nOr run **Chat: Install Plugin From Source** with this repository's URL.\n\n</details>\n\n<details>\n<summary><strong>JetBrains AI Assistant</strong> — Settings → Tools → AI Assistant → MCP</summary>\n\nUnder **Settings → Tools → AI Assistant → Model Context Protocol (MCP)**, add a server with command `npx` and arguments `-y codex-delegate-mcp`.\n\n</details>\n\n<details>\n<summary><strong>Windsurf</strong> — <code>~/.codeium/windsurf/mcp_config.json</code></summary>\n\n```json\n{\n  \"mcpServers\": {\n    \"codex-delegate\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"codex-delegate-mcp\"]\n    }\n  }\n}\n```\n\nHeads-up: Cascade caps you at 100 tools across all servers.\n\n</details>\n\n<details>\n<summary><strong>Visual Studio 2022</strong> — <code>%USERPROFILE%\\.mcp.json</code></summary>\n\n```json\n{\n  \"servers\": {\n    \"codex-delegate\": {\n      \"type\": \"stdio\",\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"codex-delegate-mcp\"]\n    }\n  }\n}\n```\n\nRequires 17.14+. Note the top-level key is `servers`, not `mcpServers`.\n\n</details>\n\n<details>\n<summary><strong>OpenCode</strong> — <code>~/.config/opencode/opencode.json</code> or project <code>opencode.json</code></summary>\n\nOpenCode does **not** use `mcpServers`. Local servers go under `mcp`, with `type: \"local\"` and `command` as one array:\n\n```json\n{\n  \"$schema\": \"https://opencode.ai/config.json\",\n  \"mcp\": {\n    \"codex-delegate\": {\n      \"type\": \"local\",\n      \"command\": [\"npx\", \"-y\", \"codex-delegate-mcp\"],\n      \"enabled\": true\n    }\n  }\n}\n```\n\n</details>\n\n<details>\n<summary><strong>Google Antigravity</strong> — <code>~/.gemini/config/mcp_config.json</code> or workspace <code>.agents/mcp_config.json</code></summary>\n\n```json\n{\n  \"mcpServers\": {\n    \"codex-delegate\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"codex-delegate-mcp\"]\n    }\n  }\n}\n```\n\nIn the IDE: **…** on the agent panel → **MCP Servers** → **Manage MCP Servers** → **View raw config**. Antigravity 2.0, IDE, and CLI share the Gemini config file. You may need to approve the server's tools on first run.\n\n</details>\n\n<details>\n<summary><strong>Kilo Code</strong> — <code>kilo.jsonc</code> (<code>mcp</code> key, not <code>mcpServers</code>)</summary>\n\nSame shape as OpenCode: `type: \"local\"` and `command` as one array.\n\n```json\n{\n  \"mcp\": {\n    \"codex-delegate\": {\n      \"type\": \"local\",\n      \"command\": [\"npx\", \"-y\", \"codex-delegate-mcp\"],\n      \"enabled\": true\n    }\n  }\n}\n```\n\nIn the VS Code extension: **Settings → MCP → Add Server → Local (stdio)**. On Windows, if `npx` is not found, use command `cmd` with arguments `/c`, `npx`, `-y`, `codex-delegate-mcp`.\n\n</details>\n\n<details>\n<summary><strong>Zed</strong> — Settings → AI → MCP Servers, or <code>context_servers</code> in Zed settings</summary>\n\n```json\n{\n  \"context_servers\": {\n    \"codex-delegate\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"codex-delegate-mcp\"],\n      \"env\": {}\n    }\n  }\n}\n```\n\nZed's native agent uses this. External ACP agents in Zed read their own MCP config unless you forward Zed's servers.\n\n</details>\n\n### Kiro and any other MCP client\n\nAdd the following server to the client's MCP config:\n\n```json\n{\n  \"mcpServers\": {\n    \"codex-delegate\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"codex-delegate-mcp\"]\n    }\n  }\n}\n```\n\nMIT © [Andrei Lungeanu](https://github.com/andreilungeanu)\n\n<sub>[Configuration](CONFIGURATION.md) · [Security](SECURITY.md) · [Privacy](PRIVACY.md) · [Terms](TERMS.md) · [Changelog](CHANGELOG.md)</sub>\n",
  "bytes": 10102,
  "sha": "bc6f0de6bd7701a7cd0cdf56805a4d94d853f12ab0f325e638c7681ddb99b717",
  "repo_slug": "andreilungeanu/codex-delegate-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_andreilungeanu_codex_delegate__28a779a3/readme"
}