Claude ↔ Codex Review Bridge

MCP server for automated code review. Claude Code writes the code, OpenAI Codex reviews it — structured feedback comes back inline, no copy-pasting between tools.

Works with your ChatGPT subscription — no API costs.

Quick Start

Free (ChatGPT subscription)

Install the Codex CLI and sign in with your ChatGPT account:

npm install -g @openai/codex
codex login

Then add the MCP server to Claude Code:

claude mcp add codex-bridge -- npx -y codex-claude-bridge@latest

API key (pay per token)

Set your API key:

export OPENAI_API_KEY=sk-...

Then add the MCP server to Claude Code:

claude mcp add codex-bridge -- npx -y codex-claude-bridge@latest

Restart Claude Code after setup. The review tools are now available.

How auth works

The SDK reads OAuth tokens from ~/.codex/auth.json (created by codex login). When no OPENAI_API_KEY is set, it uses your ChatGPT subscription automatically.

Prerequisites

• Node.js 18+ — nodejs.org
• Claude Code — code.claude.com
• Codex CLI (free path only) — installed via npm install -g @openai/codex

What You Get

Once set up, Claude Code gains five new tools:

• review_plan — Send an implementation plan for architectural review. Get a verdict (approve / revise / reject) with specific findings.
• review_code — Send a code diff for review. Get findings with file and line references.
• review_precommit — Quick sanity check before committing. Automatically captures your staged git changes.
• review_status — Check whether a review is still in progress, completed, or failed.
• review_history — Look up past reviews by session or count.

All tools return structured JSON that Claude Code can act on directly.

Usage (MCP)

In Claude Code, just describe what you want reviewed. Claude Code will pick the right tool:

Plan review:

"Review this implementation plan before I start coding."
"Check my plan for security issues and scalability risks."

Code review:

"Review the changes I just made." (Claude Code runs git diff and passes it)
"Review this diff for bugs and security issues."

Pre-commit check:

"Run a pre-commit check on my staged changes."
"Check if these changes are safe to commit."

Session continuity — pass the session_id from a plan review into a code review to maintain context across the full review lifecycle.

Standalone CLI

Run reviews directly from the terminal — no MCP setup required.

Pre-commit check (auto-captures staged changes):

npx codex-claude-bridge@latest review-precommit

Block commits on issues (CI-friendly, exits 2 on blockers):

npx codex-claude-bridge@latest review-precommit && git commit

Review a plan:

npx codex-claude-bridge@latest review-plan --plan plan.md

Review a diff:

git diff main | npx codex-claude-bridge@latest review-code --diff -

Add --json to any command for raw JSON output. Use --help to see all options.

Tools Reference

review_plan

Send an implementation plan to Codex for architectural/feasibility review.

Returns: { verdict, summary, findings[], session_id }

review_code

Send a code diff to Codex for code review.

Returns: { verdict, summary, findings[], session_id }

Findings include file and line references when available.

review_precommit

Quick pre-commit sanity check. Auto-captures staged git changes by default.

Returns: { ready_to_commit, blockers[], warnings[], session_id }

review_status

Check status of a review session.

Returns: { status, session_id, elapsed_seconds }

review_history

Query past reviews.

Returns: { reviews[] } with session_id, type, verdict, summary, timestamp per entry.

Configuration

Create .reviewbridge.json in your project root to customize review behavior:

{
  "model": "gpt-5.5",
  "reasoning_effort": "medium",
  "timeout_seconds": 300,
  "max_chunk_tokens": 8000,
  "review_standards": {
    "plan_review": {
      "focus": ["architecture", "feasibility"],
      "depth": "thorough"
    },
    "code_review": {
      "criteria": ["bugs", "security", "performance", "style"],
      "require_tests": true,
      "max_file_size": 500
    },
    "precommit": {
      "auto_diff": true,
      "block_on": ["critical", "major"]
    }
  },
  "project_context": "Your project description and constraints."
}

All fields are optional. Missing fields use the defaults shown above. Large diffs are automatically split into chunks of approximately max_chunk_tokens tokens and reviewed sequentially.

Model selection

The default model is gpt-5.5. Set the "model" field in .reviewbridge.json to use a different model:

{
  "model": "gpt-5.3-codex"
}

Any model supported by the Codex CLI works. Some common options:

The model is passed to the Codex SDK at the thread level (startThread({ model })), so each review session uses whatever model is configured at the time.

Storage

Set REVIEW_BRIDGE_DB to persist review history and session state:

export REVIEW_BRIDGE_DB=~/.codex-reviews.db

Defaults to reviews.db in the current directory. Set to :memory: for ephemeral storage.

Troubleshooting

Architecture

Claude Code ──MCP──► codex-claude-bridge ──SDK──► OpenAI Codex
                            │
                        SQLite DB
                     (review history)

The SDK (@openai/codex-sdk) internally spawns codex exec as a subprocess — there is no separate "CLI mode." Both ChatGPT subscription auth and API key auth use the same SDK path.

src/
  index.ts          → Entry point (routes to MCP or CLI)
  mcp.ts            → MCP server startup
  server.ts         → Server setup, tool registration
  cli/              → Standalone CLI (Commander.js)
  tools/            → MCP tool handlers (5 tools)
  codex/            → Codex SDK wrapper, prompts, types
  config/           → .reviewbridge.json loader
  storage/          → SQLite persistence (reviews, sessions)
  utils/            → Git diff, chunking, error types

Development

git clone https://github.com/AmirShayegh/codex-claude-bridge.git
cd codex-claude-bridge
npm install
npm test
npm run build

License

MIT