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

@candlelightgames/mcp

v0.14.0

Published

A local MCP server for Candlelight: the vocabulary for your AI to read, and tools to generate, validate and import campaigns and library content

Readme

@candlelightgames/mcp

An MCP server for Candlelight, a home for tabletop RPG campaigns. It lets an AI client you already use (Claude Desktop, Claude Code, or any other local MCP client) write campaigns and library content with you, and import them into your Candlelight account.

Candlelight has no AI of its own: the model is yours. This server gives it the vocabulary to read, a way to check its work on your machine, and a way to save it. Everything it writes goes through the same import as a file you upload, and you get a draft you can edit like any other.

Documentation: developer.candle-light.games/docs/mcp

Install

It runs on your machine, over stdio, with Node 26.13.0 or later.

Claude Code:

claude mcp add candlelight -- npx -y @candlelightgames/mcp

Claude Desktop, in claude_desktop_config.json:

{
  "mcpServers": {
    "candlelight": {
      "command": "npx",
      "args": ["-y", "@candlelightgames/mcp"]
    }
  }
}

Claude Code asks before each tool call. The read-only ones can be allowed up front, in .claude/settings.json:

{
  "permissions": {
    "allow": [
      "mcp__candlelight__reference",
      "mcp__candlelight__validate",
      "mcp__candlelight__import_preview",
      "mcp__candlelight__get"
    ]
  }
}

Sign in

Ask your AI to sign in to Candlelight (the sign_in tool), or sign in from a terminal:

npx -y @candlelightgames/mcp login

Either way you get a link to approve in your browser. The sign-in is kept in ~/.config/candlelight/ (readable only by you). logout revokes it, and status says whether you're signed in.

| Variable | What | | -------------------------------------------------------------------- | ------------------------------------------- | | CANDLELIGHT_ENV | production (the default), test, local | | CANDLELIGHT_API_URL, CANDLELIGHT_AUTH_URL, CANDLELIGHT_WEB_URL | Override one host |

Tools

  • sign_in, sign_out: sign in to your account, or out.
  • reference: the authoring guide, the vocabulary, shapes and worked examples.
  • validate: checks a document on your machine (syntax and shapes). Sends nothing.
  • import_preview: a dry run of the import: what it would create, and what it can't keep yet.
  • import: imports into your account: a new campaign, into a campaign, or your library.
  • generate: runs one of Candlelight's generators (towns, NPCs, loot, …), saving nothing.
  • get: reads your content, as JSON or exported as Turtle or JSON-LD.
  • create_character, check_character, join_campaign, add_character: for a player making their character: makes it on its system's rules a choice at a time, checks it against them, joins a campaign with an invite, and adds the character to it (the make_character prompt walks through it all).
  • character_sheet: reads a character's sheet as the app shows it, lists a campaign's characters, and exports them as Open Character Format files for other apps.
  • read_character_sheet: reads a character sheet PDF (D&D Beyond's, the official 2014 or 2024 sheet, Demiplane's Pathfinder 2e, Starfinder 2e or Daggerheart sheet) on your machine, for the campaign document. The file never leaves your machine.
  • generate_one_shot: makes a one-shot (a town, a quest and a dungeon, or a run in a city) with Candlelight's generator and saves it as a new campaign, built to be played with no GM. Read it back with get (Turtle), then add to it with import in merge mode.
  • upload_image: uploads your own art (a battlemap, a token, a handout) and gives back its URL for the document.
  • upload_link: a signed link to upload a file yourself (curl), so neither art nor a long document passes through the conversation; tools then take the uploaded document by name.
  • draw_town_map, town_map_svg: draws a town's map on your machine, and saves it or writes it out as an SVG.

The author_campaign prompt starts a campaign from a premise.

Licence

MIT. The worked examples it carries (the What the River Owes campaign and a library pack) are CC BY 4.0. See LICENSE.