npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@1key4ai/mcp-review

v0.12.12

Published

Plan review for Claude Code via 1K4. Submit plans for external review with structured findings.

Readme

@1key4ai/mcp-review

Plan review for Claude Code via 1K4.

Two or more AI models review your implementation plans and return structured findings with severity and evidence. Setup is one command; reviews run automatically during plan mode.

Setup

  1. Get a single-use setup token at 1key4ai.com/install (10-minute TTL; exchanged for your API key locally, so your long-lived key never goes on the command line).
  2. Run the setup command:
npx -y -p @1key4ai/[email protected] mcp-review setup --setup-token <token>

This registers the MCP server, adds a /review-plan skill, and configures Claude Code to review plans automatically. Works globally across all your projects. The install is pinned to an exact version; rerun mcp-review setup to move to a newer release.

For staging:

npx -y -p @1key4ai/[email protected] mcp-review setup --setup-token <token> --api-base https://staging.1key4ai.com

Legacy: --api-key sk-... is still accepted for backward compatibility, but the setup-token flow is preferred so a long-lived key never lands in shell history or process lists.

Or add to your MCP config manually (setup writes this for you — the API key lives in env, never on the command line):

{
  "mcpServers": {
    "1k4-review": {
      "command": "npx",
      "args": ["-y", "-p", "@1key4ai/[email protected]", "mcp-review"],
      "env": {
        "K4_API_KEY": "your-key-here"
      }
    }
  }
}

What happens

After setup, Claude Code automatically reviews plans before presenting them for approval. Multi-model reviewers (Gemini, GPT, Grok) return findings at three severities: critical (ship-blocker), important (correctness gap), advisory (style). Claude Code synthesizes findings and iterates until consensus. Say "skip review" to opt out for any specific plan.

Tools included

This package now ships the full unified 1K4 surface:

  • 1k4_review_plan: Multi-model plan review with structured findings
  • 1k4_advisors: List available advisor personas and their capabilities
  • 1k4_consult: Ask a single AI advisor a freeform question (code review, security audit, design feedback)
  • 1k4_brainstorm: Multi-round, multi-advisor brainstorm with cross-pollination
  • 1k4_send_message / 1k4_wait_for_message / 1k4_get_session_status / 1k4_list_files / 1k4_get_file / 1k4_answer_questionnaire: Studio agent bridge
  • lab_create_file / lab_edit_file / lab_read_file / lab_list_files / lab_create_folder / lab_move_file / lab_create_document / lab_edit_document / lab_create_presentation / lab_create_mockup / lab_git / lab_review_document / lab_update_file / lab_vm_ops / lab_deploy / lab_questionnaire / lab_web_fetch / lab_data_analysis: Lab workspace operations
  • Plus dynamically-discovered tools from the backend catalog

Two install paths (mcp-review vs cc-bridge)

@1key4ai/mcp-review ships the same full unified tool surface as @1key4ai/cc-bridge. Both packages re-export the same compiled MCP server. The only difference is the entry written to ~/.claude.json:

| Package | mcpServers key | Tool prefix in Claude Code | |---|---|---| | @1key4ai/mcp-review | 1k4-review | mcp__1k4-review__1k4_review_plan etc. | | @1key4ai/cc-bridge | 1k4-bridge | mcp__1k4-bridge__1k4_review_plan etc. |

Existing mcp-review users — updating

New installs are version-pinned (see Setup above). To move a pinned 1k4-review entry to a newer version, rerun mcp-review setup. (If your config predates pinning and still has @latest in its args, it will resolve the registry on each session start; the pinned form is now preferred and is what setup writes.) Tool prefixes stay mcp__1k4-review__* either way (no client-side breakage).

New users — recommended: cc-bridge

If you're starting fresh, install @1key4ai/cc-bridge instead (get a setup token at 1key4ai.com/install):

npx -y -p @1key4ai/[email protected] cc-bridge setup --setup-token <token>

The cc-bridge entry uses the cleaner short args form (["-y", "@1key4ai/[email protected]"]) and serves as the marketing name for the unified product going forward.

Migrating mcp-review → cc-bridge (optional)

To consolidate your existing 1k4-review entry into a single 1k4-bridge entry:

npx -y -p @1key4ai/[email protected] cc-bridge setup --setup-token <token>

cc-bridge setup detects the existing 1k4-review (and 1k4-lab/1k4-studio if present), prompts Proceed? [y/N], backs up ~/.claude.json to a timestamped file, and writes a single mcpServers["1k4-bridge"] entry preserving your captured env vars. Migration is opt-in; skip it and mcp-review keeps working indefinitely.

Your first review is free

2 rounds, on us.

Pricing

Pay per token at below list price. Credits never expire.