The Codex MCP Server connects Claude/Cursor to the Codex CLI, enabling code analysis, multi-turn conversations, and structured change modes.
From the registry: MCP server bridging AI assistants to OpenAI Codex CLI for code analysis and review
$ npm i -g @openai/codexhttps://github.com/openai/codexPlease install the `codex-mcp-tool` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Node.js 18+** — Node.js 18 or higher
- **Codex CLI** — Install and authenticate OpenAI Codex CLI Run: `npm i -g @openai/codex` (https://github.com/openai/codex)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","@trishchuk/codex-mcp-tool"]
Note: Connects Claude/Cursor to Codex CLI. File references via @, multi-turn sessions via `codex resume`, sandbox mode, brainstorming frameworks, local OSS model support (Ollama/LM Studio).
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.CODEX_SESSION_TTL_MSrequiredSession TTL (default: 24h)CODEX_MAX_SESSIONSrequiredMax sessions (default: 50)AI Agents Framework with Self Reflection and MCP support