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

@thedeck/mcp

v0.1.5

Published

The Deck's MCP server. It lets your AI agent draft tasks, send blanked example copies, propose tests, check your tasks and their passing entries, run the pre-check on your entry, and try passing entries on your real data. It acts as you, with the same rig

Readme

@thedeck/mcp

The Deck's MCP server. It lets your AI agent draft tasks, send blanked example copies, propose tests, check your tasks and their passing entries, run the pre-check on your entry, and try passing entries on your real data. It acts as you, with the same rights you have on the site.

An agent can never save a card, post a task live, accept an entry, pitch in or pay anyone. You do those on The Deck yourself.

Connect

Claude Code:

claude mcp add thedeck -- npx @thedeck/mcp

Codex:

codex mcp add thedeck -- npx @thedeck/mcp

GitHub Copilot in VS Code:

code --add-mcp '{"name":"thedeck","command":"npx","args":["@thedeck/mcp"]}'

The first time your agent uses a tool, your browser opens The Deck's consent page. Sign in, check what the agent may do, and press Allow. The sign-in is saved in ~/.thedeck/credentials.json; disconnect the agent any time in Settings › Agent.

ChatGPT and other clients that only connect to remote servers use https://thedeck.dev/mcp instead. That address has the poster tools and deck.report_issue only: nothing there runs on your computer. In Grok, open Connectors, choose New Connector, then Custom, enter that address and sign in to The Deck when asked.

Tools

| Tool | For | Runs | |---|---|---| | deck.post_draft | posters | The Deck | | deck.add_example_copy | posters | checks the copy here, then The Deck; over /mcp, after you approve the exact copy in the chat | | deck.propose_tests | posters | The Deck, after you approve the test plan in the chat | | deck.list_quests | posters and builders | The Deck | | deck.get_task_status | posters | The Deck | | deck.get_passing_entries | posters | The Deck | | deck.try_on_real_data | posters | a sandbox on this computer | | deck.run_precheck | builders | a sandbox on this computer | | deck.report_issue | posters and builders, during the beta, with your yes | The Deck |

Real files and real data never leave your computer: only blanked copies and scores do.

The local sandbox

deck.run_precheck and deck.try_on_real_data run entries the way The Deck's runner does, in a Docker container with no network. Install Docker and build the sandbox image once from this repository:

docker build -f runner/Dockerfile --target sandbox -t thedeck-sandbox .

An entry folder needs a deck.json naming the command that runs it, for example {"run": ["python", "read_invoices.py", "{input}", "{output}"]}. Without {output}, what the program prints is its answer.

For deck.try_on_real_data, put each real input beside its right answer with the same name, such as invoice-01.pdf and invoice-01.csv.

Pre-check from a terminal

npx -p @thedeck/mcp thedeck precheck <quest id> [entry folder]

Settings

THEDECK_URL points the server at another copy of The Deck, for example http://127.0.0.1:3000 locally.