reviewzy

human-in-the-loop mcp review for user-facing text: agents file, a human approves, later sessions apply

bulk-audit and rewrite user-facing copy across CLIs, TUIs, web UIs, and websites; prose authorship stays human

reviewzy is a self-hosted dashboard and mcp server for human-in-the-loop copy review. a coding agent files the exact strings it wants to write or rewrite. a human authors or approves each one on the dashboard. a later agent session fetches the approved words and applies them in place. no i18n keys, no content layer: each entry points at the string where it already lives.

file an entry:

{
  "project": "my-app",
  "entries": [
    {
      "repo": "https://github.com/me/my-app",
      "file": "src/cli/main.ts",
      "anchor_text": "error: something went wrong",
      "agent_draft": "error: could not reach the reviewzy daemon",
      "file_content": "#!/usr/bin/env bun\nconsole.error(\"error: something went wrong\")\n",
      "constraints": { "max_len": 48, "tone": "plain, lowercase" }
    }
  ],
  "filed_by": "help-text-audit"
}

the call answers with the entry as draft and a dashboard link for the batch:

{
  "batch_id": "01M060XY9GNK6ANVENN4Y4MK7N",
  "results": [
    { "id": "01M060XY9GNK6ANVENN4Y4MK7P", "status": "draft", "deduped": false, "updated": false }
  ],
  "dashboard_url": "http://127.0.0.1:3123/?project=my-app"
}

Why

• file + snippet anchors, no i18n keys: apply-back is a targeted replace in place

• humans author, agents apply: the status machine is server-enforced; only the dashboard reaches approved or rejected

• per-project style guide as an mcp resource: merged with the global guide, embedded in fetch_approved

• append-only revision history: every save is undoable; history survives archiving

• ntfy and webhook notifications, archive retention: one ping per filing batch; applied entries archive after ARCHIVE_AFTER_DAYS

Related MCP server: approval-gate

How it works

Install

bunx reviewzy@latest

requires bun >= 1.3 (the store is bun:sqlite, bun-only; no npx form). the shim spawns one shared daemon per machine on first use.

from a checkout:

bun install
bun run daemon

as a Claude Code plugin

the repo is a plugin: it registers the MCP server and adds a /reviewzy slash command plus the reviewzy skill.

/plugin marketplace add uwuclxdy/reviewzy
/plugin install reviewzy@reviewzy

same bun requirement as the npm form.

Usage

curl http://127.0.0.1:3123/health

{"name":"reviewzy","version":"0.1.0","pid":4172598,"nonce":"881f0e93-8dde-4c75-b559-d2e3d3b223f0","startedAt":"2026-08-16T19:31:28.640Z"}

open http://127.0.0.1:3123/ for the dashboard.

Configuration

copy .env.example to .env and edit. every key is optional; a bad value refuses startup.

a credential left unset keeps that surface loopback-only with a startup warning.

Integrations

point an mcp client at reviewzy to start filing:

{
  "mcpServers": {
    "reviewzy": {
      "command": "bunx",
      "args": ["reviewzy@latest"]
    }
  }
}

the endpoint speaks the stateless 2026-07-28 mcp revision.

Comparison

the blocking human-in-the-loop mcp family pops a dialog per call: no queue, no persistence, no dashboard.

FAQ

How do I approve AI-generated text before it lands in my code? the agent files strings as drafts, you author or approve them on the dashboard, the agent applies.

Can an AI agent rewrite my CLI help text without i18n keys? yes. entries anchor on the exact current strings; apply-back is a targeted replace.

How do I bulk-rewrite all user-facing copy in a codebase? file batches per project, group by project or batch on the dashboard, approve in bulk with a before/after diff, then let a later agent session fetch and apply.

How do I update the style guide my agents read? edit it on the dashboard at /style-guide. a saved edit reaches agents in up to 60 seconds.

Development

bun run check  # tsc --noEmit && bun test

License

AGPL-3.0. self-hosted stays self-hosted; a saas wrapping it publishes its changes.