Why CC GUI Is the Ideal Companion for Claude Code and Codex in IntelliJ IDEA

Problem

JetBrains IDE users have to switch between the editor and a separate terminal to talk to Claude Code or Codex, which interrupts the development flow.

Official ACP integration vs. CC GUI

JetBrains provides an Agent Client Protocol (ACP) integration that runs the Claude Code / Codex CLI inside the IDE, offering a lightweight experience without GUI features such as session management, image input, or skill extensions.

CC GUI (formerly Claude Code GUI) is an MIT‑licensed plugin (≈3.5 k Stars on GitHub) that embeds the full capabilities of Claude Code and Codex into a dedicated panel inside IDEA.

Key capabilities of CC GUI

Switch instantly between Claude Code and Codex without changing plugins.

Use @file to attach files, images, or screenshots, providing richer context than raw CLI commands.

View code changes directly in IDEA’s Diff panel and jump to the corresponding line.

Track token usage and cost per conversation, making expense monitoring transparent.

Built‑in slash commands and MCP server extensions for custom workflows.

Comparison of positioning and trade‑offs

Core positioning : ACP runs the agent in the IDE; CC GUI provides a complete visual workbench.

Key capabilities : ACP focuses on diff view and context sharing; CC GUI adds session management, image input, a skill system, and MCP support.

Target users : ACP suits heavy CLI users; CC GUI targets developers who want to finish tasks entirely inside the IDE.

Trade‑offs : ACP is lightweight and close to the CLI; CC GUI is richer but adds a GUI layer.

Three‑step installation

Open Settings → Plugins, search for “CC GUI”, and install the version with the highest download count (≈385.6 k).

Configure a provider using one of four methods:

Create an Anthropic API key in the console (different from a Claude.ai subscription).

Import an existing endpoint from the local ~/.claude/settings.json file.

Run cc-switch to import community‑maintained provider settings.

Specify a custom third‑party endpoint for domestic users.

Start a conversation from the right‑hand panel, e.g., ask the AI to “analyze the current project structure”.

/plan mode – designing a payment integration

In /plan mode the AI first thinks through the task and returns a detailed design without touching code. Example command: /plan 设计下银联的接入方案 The AI scans the project, reads the PaymentService implementation, extracts key points from the UnionPay documentation, and produces a checklist:

Files to modify

New classes to add

Required SDKs

Where to place signatures and encryption

How to handle callbacks and async notifications

After review, the user can switch to /agent mode to let the AI apply the changes, or abort with git reset if the plan is unsatisfactory.

Token consumption statistics

Simple dialogue (5 rounds): ~15 K tokens

Code review (~100 lines): ~25 K tokens

Planning a medium‑size project ( /plan): ~40 K tokens

AI Commit and AI Review

AI Commit generates Conventional Commits‑style messages from staged diffs, accelerating commit creation by about five times. AI Review runs the AI over a diff before a commit or pull request, flagging boundary conditions, null‑pointer risks, potential infinite loops, and naming inconsistencies.

MCP server configuration

Enter the server address, headers, and authentication once; the same mcp.json is shared with Claude Desktop and Cursor. Installing the Chrome DevTools MCP extension lets the agent invoke Chrome for front‑end testing and debugging, which is useful for bugs that require a logged‑in session.

CC GUI vs. Qoder vs. CodeBuddy

Nature : All three are independent AI‑coding agents; CC GUI is a GUI shell for CLI agents, while Qoder (Alibaba) and CodeBuddy (Tencent) are closed‑source agents.

Open‑source : CC GUI is MIT‑licensed; the others are proprietary.

Model support : CC GUI can use Claude, Codex, or custom models; Qoder and CodeBuddy ship with built‑in models.

Entry barrier : CC GUI requires an existing Claude/Codex subscription; Qoder offers a free tier with registration; CodeBuddy provides a free personal edition.

Strengths : CC GUI reuses existing subscriptions and is community‑driven; Qoder is deeply optimized for the Java ecosystem; CodeBuddy integrates tightly with Tencent’s cloud services.

Install all three if desired; they do not conflict.

Limitations

The quality of the AI’s output depends on the accuracy of the supplied context (e.g., correct use of @file).

Developers must clearly define project boundaries; the AI cannot infer business constraints on its own.

Generated code still requires human review—AI can write code, but reviewing it is the real challenge.

Getting started

For newcomers, start with well‑scoped tasks such as adding unit tests, generating boilerplate, outlining module logic, or converting screenshots to initial code.

Project repository

https://github.com/zhukunpenglinyutong/jetbrains-cc-gui