# Codex CLI

> Use this tool when you need to integrate AI-powered code assistance into your development workflow, leveraging Codex's capabilities for tasks like code execution, brainstorming, and refactoring. It solves problems related to AI-assisted coding, code analysis, and automated refactoring, accepting commands and code inputs and producing formatted, chunked responses. Ideal for use in MCP-compatible environments, it streamlines AI-driven development workflows and enhances productivity.

Canonical page: https://skillsregistry.net/skills/cexll-codex-cli  
JSON: https://api.skillsregistry.net/v1/skills/cexll-codex-cli

## Description

A TypeScript MCP server that bridges Claude and other AI clients with the Codex CLI, OpenAI's AI-powered code assistant. Built by Taras Trishchuk, it provides tools for executing Codex commands, brainstorming sessions, and handling large responses through chunked delivery, with support for change mode operations that parse and format code edits into structured chunks for easier application. The implementation includes timeout prevention, caching for multi-chunk responses, working directory resolution, and integration with Codex's sandbox modes and model selection, making it useful for AI-assisted development workflows, code analysis, and automated refactoring tasks within MCP-compatible environments.

## Trust

- **Trust score (0–1):** 0.75
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/cexll-codex-cli)
- **Repository:** <https://github.com/cexll/codex-mcp-server>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "cexll-codex-cli"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/cexll-codex-cli` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/cexll-codex-cli/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt