Supercharging Codex with JetBrains MCP at Skyscanner | OpenAI Developers
Jan 11, 2026

Summary
This post details the integration of OpenAI's Codex CLI with JetBrains IDEs via the Model Context Protocol (MCP) server. This integration allows Codex to access IDE context, such as analyzing files for errors and warnings using IntelliJ inspections and executing predefined run configurations (unit tests, linters, formatters). The post highlights how this provides faster feedback loops, reduces back-and-forth prompting, and leads to higher-quality suggestions by enabling Codex to leverage the same feedback mechanisms human developers use. It also includes custom agent instructions to run tests, linting, and formatting after code edits.
More from the Agentic Execution Environment trail
- Bringing my LED display to life with GPT-Live-1 and Codex | OpenAI Developers
- Rethinking skills and prompts for GPT-6 Astra | OpenAI Developers
- Meet Rosalind Workbench: Empowering every scientist to be their own research team | OpenAI Developers
- Automating repetitive work at OpenAI with Codex
- Codex as a platform: build on the open agent harness | OpenAI Developers