ly8427/mcp-review-board
by Various
MCP review board that lets different coding agents review each other — object → revise → pass, append-only audit trail. For Claude Code, Codex, OpenCode, Trae, ZCode.
MCP
ly8427/mcp-review-board
Added 10 Oct 2026
Overview
MCP review board that lets different coding agents review each other. It implements an object, revise, pass workflow with an append-only audit trail. Supports Claude Code, Codex, OpenCode, Trae, and ZCode.
Best for
Best for
Teams running multiple coding agents that need a lightweight review handoff process.
Use cases
- Coordinate review handoffs between Claude Code and Codex
- Maintain an append-only audit trail of agent revisions
- Enforce a pass or revise gate before merging agent output
How to use
Install
python3 -m venv .venv && .venv/bin/python -m pip install -r requirements.txt Tools exposed
get_protocollist_participantscreate_threadpost_commentreply_commentlist_threadsget_threadset_statuslist_comments_sinceset_verdictbump_revisionset_quorumreliability_profileREVIEWBOARD_PORTREVIEWBOARD_HOSTREVIEWBOARD_DBREVIEWBOARD_THREAD_CAPREVIEWBOARD_UNACKED_REISSUE_MINREVIEWBOARD_AUTO_ACK_REISSUE_HOURS
Tested with
Claude Code, Cursor
Notes
MCP review board that lets different coding agents review each other. It implements an object, revise, pass workflow with an append-only audit trail. Supports Claude Code, Codex, OpenCode, Trae, and ZCode.
0 stars on GitHub. Last updated 2026-10-08. Licensed MIT.
Use cases
- Coordinate review handoffs between Claude Code and Codex
- Maintain an append-only audit trail of agent revisions
- Enforce a pass or revise gate before merging agent output
Pros
- Works across multiple coding agents
- Append-only audit trail provides accountability
- Simple three-step workflow
Cons
- No GitHub stars yet, so adoption is unproven
- Requires MCP setup for each supported agent
- Limited to the listed agents
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Works across multiple coding agents
- Append-only audit trail provides accountability
- Simple three-step workflow
Cons
- No GitHub stars yet, so adoption is unproven
- Requires MCP setup for each supported agent
- Limited to the listed agents
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.
