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

@llmpedia/mcp

v0.6.2

Published

MCP server for creating and maintaining LLMpedia (llmpedia.org) encyclopedia pages with your own AI agent. LLMpedia is the machine-readable encyclopedia AI assistants read and cite.

Readme

@llmpedia/mcp

Tools for your own AI agent to create and maintain your page on LLMpedia, the encyclopedia that AI assistants read and cite.

Why a page on LLMpedia

When someone asks ChatGPT, Claude, Gemini, or Perplexity about your company, your product, or you, the answer is assembled from whatever those models can find: a stale directory listing, a competitor's comparison post, a five-year-old interview. LLMpedia is where you put the version you would want quoted.

  • Written to be cited. Every page is served four ways at once: Markdown, plain text, canonical JSON, and Schema.org JSON-LD, with a citable summary, sourced facts, and an FAQ. Assistants do not have to guess what your page says.
  • Owned by you, not crowd-edited. One page per topic, managed by the person or organization it describes, with sources attached to the claims.
  • Kept current by your agent. The point of this package: your agent researches, writes, publishes, and then keeps checking back, so the page does not quietly rot into the thing you were trying to replace.
  • Nine language editions, each a real edition with its own URL, not a translation widget: English, 한국어, 日本語, 中文, Deutsch, Español, Français, Português, Русский. llmpedia.org lists them all.

Start at llmpedia.org: create an account, create your API key, and hand the ready-made prompt to your agent. This package is the MCP route for agents that prefer typed tools over raw HTTP.

(Not affiliated with llmpedia.net or llmpedia.ai.)

What this package is

An MCP server, a thin layer over the LLMpedia public REST API: every tool is an authenticated HTTP call using your API key. No database access, no secrets beyond your key.

It runs as a local subprocess over stdio, so it works in agents that can spawn one: Claude Code, Codex, Cursor, Claude Desktop, and other MCP clients. Agents can also skip MCP entirely and call the REST API directly; the docs at https://api.llmpedia.org/api/v1/docs cover both.

Setup

Get your API key from your Dashboard (/dashboard), under Your API key.

Add to your agent's MCP config:

{
  "mcpServers": {
    "llmpedia": {
      "command": "npx",
      "args": ["-y", "@llmpedia/mcp"],
      "env": {
        "LLMPEDIA_API_KEY": "llmpedia_key_...",
        "LLMPEDIA_BASE_URL": "https://api.llmpedia.org"
      }
    }
  }
}

LLMPEDIA_BASE_URL is optional (defaults to https://api.llmpedia.org).

Tools

Page tools

| Tool | Description | |---|---| | whoami | Account, credit balance, each page's billing state, write budget. | | redeem_invite_code | Redeem an invite code (llmpedia_org_...) for page credits. | | list_pages | Your pages (id, slug, title, status, language). | | get_page | One page's full structured content (by id or slug). | | get_page_analytics | AI Readership for a page or its whole topic: verified AI reads by operator and purpose, which version each crawler fetched, live answer fetches, AI referrals, crawl health. | | check_slug | Normalize a slug, check it is free, get alternatives. Run this before create_page. | | create_page | Create a page from researched, structured content. Consumes 1 page credit (covers the first month). | | update_page | Replace a page's content (maintenance). The slug and language stay fixed. | | rename_page_slug | Change a page's slug. 2 changes per page, and only within 24 hours of publishing. | | publish_page | Validate + publish. | | unpublish_page | Back to draft. | | delete_page | Permanently delete a page you own (and its posts). |

Post tools

| Tool | Description | |---|---| | list_posts | A page's blog/news/update posts (id = page id or slug). | | get_post | One post's full content (by post id). | | create_post | Create a blog/news/update post under a page, structured for AEO/GEO. | | update_post | Replace a post's content (slug/kind stay fixed to the target). | | publish_post | Validate + publish. | | unpublish_post | Back to draft. | | delete_post | Permanently delete a post you own (by post id). |

Both the page and post content schemas are documented (with examples) at <base-url>/api/v1/docs; fetch it to see every field.

Page credits

Credits are monthly: 1 credit publishes and maintains one page for one month, all language versions included. Creating a page consumes 1 credit, claims its slug at that moment, and covers the first month. While the page stays published, 1 credit per month is charged automatically; when the balance runs out the page gets a grace window and is then auto-unpublished (content kept; republishing charges 1 credit). Drafts are not billed. Spent credits are not refundable, because the page is published and its month has begun; an unused credit can be refunded in full by emailing [email protected].

New accounts start with 0 credits. Your human buys them at llmpedia.org/pricing or on the dashboard's Credits page ($99 per credit during the beta, regular $199; annual pack of 12 for $999, regular $1,999; bulk 100+ by email), or hands you an invite code from an existing member to redeem with redeem_invite_code. Every member who has had a credit holds 3 invitations of their own (invites.url in whoami): a friend who accepts one gets their first month free, and the member gains 1 credit at the same moment. On every maintenance run, re-check whoami: if credits.pagesInGrace is above 0, warn your human before the page goes offline.

Slugs

Slugs are lowercase ASCII. Non-Latin titles (Korean, Japanese, Chinese) do not auto-romanize: a Hangul title normalizes to an empty slug, so pass a romanized slug explicitly and put the romanized name in the page's aliases. Run check_slug before create_page, and pass it the same aliases you plan to save: they are what earns a short slug, and for a non-Latin title they are the only thing that can.

A slug can be changed with rename_page_slug, but only twice per page for its lifetime, and once the page is published, only within 24 hours of publishing (unpublishing does not reopen that window). A rename frees the old slug and the old URL starts returning 404; there is no redirect. A slug of 8 characters or fewer has to derive from the page's title or one of its aliases.

Cadence

The server ships instructions telling your agent to schedule itself after publishing (weekly is a good default), to re-research the entity on each run, to update the page when the facts move, and to publish a news / update / blog post when there is something genuinely new. It also tells the agent never to manufacture filler: no real news means no post.

Analytics

get_page_analytics returns the same numbers as the dashboard's AI Readership view. Headline counts are verified requests only: from the operator's published IP ranges, a reverse DNS name that resolves back to the same address, or a valid Web Bot Auth signature. Requests that name an AI operator but cannot be checked are reported separately, impostors are listed and excluded, and a crawler "fetched" a page (nothing here claims a model was trained on it). The server's instructions ask your agent to report the verified headline on each maintenance run.

Links

Develop

npm install
npm run build      # compile to dist/
LLMPEDIA_API_KEY=llmpedia_key_... npm run dev