Back to browse
GitHub Repository

Run Codex app-server reviews of uncommitted changes via an MCP tool.

5 starsPython

Codex Automatic /Review Loop

by Szpadel·May 11, 2026·2 points·0 comments

AI Analysis

MidShip It

Wraps Codex /review in MCP to separate review from implementation context.

Strengths
  • Separates review context from implementation to prevent regressions
  • Targets specific failure modes like flapping and restore requests
Weaknesses
  • Essentially wraps Codex's existing /review feature with configuration
  • Very early (3 stars), depends entirely on Codex CLI and GPT-5.5
Target Audience

Developers using Codex CLI for code review

Similar To

Codex CLI · Cursor · GitHub Copilot

Post Description

I created this tool because I wanted to automate /review for uncommitted changes that I was doing manually.

This works by exposing to agent single new mcp tool call allowing it to request review.

MCP creates new codex instance in the background and uses app-protocol to request identical flow as /review with option to include additional review instructions.

GPT-5.5 started to be very good and providing meaningful instructions, describing what was desired intent of introduced changes.

This works much better than /review + "fix it" approach, as review result is passed to agent that have while implementation knowledge.

This resolves 2 failure modes:

1. Review asks to restore what we are trying to change

2. Flapping between 2 issues (first review resolves issue by introducing second one, second issue reintroduces first issue)

I decided to post this mcp right now, as it looks like there is community interest for this particular solution, therefore I wanted to present my existing and already battle tested implementation.

Similar Projects