aeo-toolkit

mcp
Guvenlik Denetimi
Basarisiz
Health Uyari
  • License — License: Apache-2.0
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 5 GitHub stars
Code Basarisiz
  • rm -rf — Recursive force deletion command in .github/workflows/plugin-branch.yml
  • rimraf — Recursive directory removal in apps/chrome-extension/package.json
Permissions Gecti
  • Permissions — No dangerous permissions requested

Bu listing icin henuz AI raporu yok.

SUMMARY

Open-source suite of ten AEO / technical-SEO / AI-visibility tools — a TypeScript monorepo (crawl→parse→score engine + MCP servers + content agents).

README.md
AEO Toolkit mark: a faceted sphere in dusk and ink

AEO Toolkit

The next big thing will be a lot of small things.

Open-source AI search optimization: 44 small checks that decide whether ChatGPT, Claude and Perplexity cite you.

The AEO Toolkit homepage in pixel art: 'The next big thing will be a lot of small things' above a dithered figure pushing a faceted sphere up a slope

TypeScript
License: Apache 2.0
Made by Advance Labs
MCP servers live
Brand
Chrome Web Store

Open-source TypeScript packages for Answer Engine Optimization (AEO), Generative Engine Optimization (GEO), and AI citation visibility. Contributions welcome, see CONTRIBUTING.md.

Open core. This repo is the open-source half of the AEO Toolkit: the audit engine, crawler,
parser, schema validator and the Chrome extension, all Apache-2.0 and published to npm. The
hosted platform behind advancelabs.dev/tools and the two
MCP servers (the console, OAuth, billing, the Google and Bing integrations) moved to a
private repository on 2026-10-20. Code published here before that date stays Apache-2.0.

Try it without installing anything: the six browser tools run free in the browser at
advancelabs.dev/tools, with no sign-up and no account.
Point the auditor at a URL and it returns a weighted, per-rule report in about a minute.
Want it done for you? Advance Labs runs a monthly AEO retainer.
Want the data underneath? DataForAEO is data for AEO from Advance Labs: measured AI-assistant demand per page, AI answers and citations, and the AI crawler list.

The hosted side is six browser tools (technical audit, E-E-A-T scan, llms.txt generator,
GA4 + GSC chat, backlink graph, authority) and two MCP servers (research, toolkit)
exposing 38 distinct tools to Claude or any MCP client. They are proprietary and run on
advancelabs.dev. This repo is the open core: the audit engine packages, the
Chrome extension and the skills. See
docs/reference/tools.md for the full map.


What it looks like

The hosted site is drawn in dithered pixel art: a figure pushing a faceted sphere up a slope under a dusk sky.

Step one, crawl and score: a pixel-art faceted sphere beside a dark audit panel The 44 small things: a category list beside a carousel of check cards, each with its fix
Crawl and score. Up to 50 pages against every rule. 44 small things. Pick a category and flip through the checks. The scoring engine is Apache-2.0.
The LLM and Technical SEO Audit tool: a URL field and Run audit button on a dark panel The Track page: the pixel figure pushing a dusk-coloured sphere beside the heading about who AI recommends
The audit tool. Free, no sign-up. Track. See who AI recommends.
The MCP page: Connect the AEO Toolkit to your AI client

What is AEO?

Answer Engine Optimization (AEO) is the practice of structuring your content so that AI assistants (ChatGPT, Perplexity, Claude, Gemini) cite your site when answering questions in your domain. Traditional SEO gets you ranked on the blue-link results page. AEO gets you quoted in the AI answer.

As AI-powered search becomes the default discovery layer, AEO is the new SEO.


The audit

The hosted technical audit runs 44 checks (31 technical SEO + 13 AEO) across crawlability,
AI-bot access, structured data, metadata and answer readiness, scored out of 100, with a prioritised
fix list and templates for any crawl-hint file you're missing. The E-E-A-T scan is a separate
tool that scores 14 signals. The engine defines 58 in total (44 + 14), but the audit itself
runs 44. Free, no account, and your data stays yours.


The Chrome extension

AEO/GEO Auditor puts the same engine on your toolbar. Open any page, click the icon, and get a 0 to 100 AI-readiness score with a letter grade and a list of what to fix. Export it as a PDF.

It runs auditRules from packages/scoring/src/audit.ts: 44 checks across 9 categories (31 technical-SEO + 13 AEO) from extension 0.3.0, built on scoring 0.3.x. The Chrome Web Store serves 0.3.2 (checked 2026-11-17), so the store build runs 44. The 14 E-E-A-T signals are a separate scorer the extension does not run, 58 is the engine total (44 + 14), not what any one audit runs.

Everything happens in your browser. No account, no server, no analytics, no telemetry. The only network requests are to the audited site's own robots.txt, sitemap.xml, and llms.txt, which is what the host permission is for. Nothing is stored, because nothing is sent.

Build it yourself:

pnpm --filter @advance-labs/chrome-extension package
# → apps/chrome-extension/aeo-extension.zip, loadable via chrome://extensions (Developer mode → Load unpacked, on dist/)

Packages

Package Description
@advance-labs/crawler Multi-threaded web crawler with robots.txt compliance, sitemap parsing, and per-host rate limiting
@advance-labs/html-parser Extracts meta tags, Open Graph, Twitter Cards, headings, images, links, and JSON-LD from HTML
@advance-labs/schema-validator Validates Schema.org JSON-LD structured data against known types
@advance-labs/scoring Scores pages on 44 technical SEO and AEO checks, plus a separate 14-signal E-E-A-T scorer, with per-rule explanations

Plus @advance-labs/net-guard and @advance-labs/types. The one
application here is apps/chrome-extension; the hosted console is not open source.


Quick Start

Six packages are published to npm and usable on their own:

npm i @advance-labs/scoring      # the 44-check audit engine
npm i @advance-labs/net-guard    # SSRF-safe fetch: re-checks every redirect hop
npm i @advance-labs/crawler      # polite crawler with robots.txt + rate limiting
npm i @advance-labs/html-parser
npm i @advance-labs/schema-validator
npm i @advance-labs/types        # shared types, a dependency of the above

The hosted tools at advancelabs.dev/tools need no install at all.

git clone https://github.com/Advance-Labs/aeo-toolkit.git
cd aeo-toolkit
pnpm install
pnpm build          # turbo builds every package
pnpm test           # the full suite, no network

Read the full documentation at docs.advancelabs.dev/aeo-toolkit.

Once built, the packages compose like this:

import { crawl } from '@advance-labs/crawler'
import { parseHtml } from '@advance-labs/html-parser'
import { analyzeStructuredData } from '@advance-labs/schema-validator'
import { buildAuditReport } from '@advance-labs/scoring'

const result = await crawl('https://example.com/', { maxPages: 2 })
const html = result.pages.filter((p) => p.ok && p.body && p.contentType?.includes('html'))

const report = await buildAuditReport(
  {
    crawl: result,
    pages: html.map((p) => parseHtml(p.body, p.finalUrl)),
    structuredData: html.map((p) => analyzeStructuredData(p.body, p.finalUrl)),
    mode: 'full-site',
  },
  { durationMs: 0, version: '1.0.0' },
)

console.log(report.url, report.score.overall, report.score.grade)
console.log(report.topFixes.slice(0, 3).map((f) => f.title))

Agent skills: AEO for coding agents

The MCP servers tell an agent what is wrong. The skills tell it how to fix it in
the stack it is working in, then how to check the fix landed. There are 24, and every one of the 58
scoring rules has exactly one owning skill (skills/rule-map.json, enforced
in CI). The fixes cover AI crawler access, server rendering, llms.txt, indexability, Organization
and author markup, answer-first content, metadata, freshness, trust signals and citation earning,
plus measurement workflows on Search Console, Bing, GA4 and Perplexity.

One command installs all the skills and the two MCP servers into Claude Code:

/plugin install aeo-toolkit --marketplace Advance-Labs/aeo-toolkit

Or add the marketplace first and pick it from the list:

/plugin marketplace add Advance-Labs/aeo-toolkit
/plugin install aeo-toolkit@advance-labs

The toolkit server asks you to sign in to your AEO Toolkit account on first use (/mcp → Authenticate). Connect Google and Bing on your project in the AEO Toolkit dashboard, and save AI provider keys under Settings; the server uses them, so you never paste a key into chat. Other agents can
copy any skills/<name>/ directory into their own skills folder. Every skill is also published
as a readable guide at docs.advancelabs.dev/aeo-toolkit/skills.

Already added the servers with claude mcp add? The plugin registers its own copies
(plugin:aeo-toolkit:*), so remove the manual ones to avoid duplicate tools.


Connect the MCP servers

Listed in the official MCP Registry
as dev.advancelabs/aeo-research and dev.advancelabs/aeo-search (titled "AEO Toolkit").

The two MCP servers are hosted, not installed. They are Streamable-HTTP endpoints, so there is
nothing to npm install and no local process to run. Point any MCP client at the URL.

Claude Code: one command per server:

claude mcp add --transport http --scope user aeo-research https://aeo.advancelabs.dev/api/mcp/research/mcp
claude mcp add --transport http --scope user aeo-toolkit  https://aeo.advancelabs.dev/api/mcp/search/mcp

Drop --scope user to register them in the current project only. Check the result with
claude mcp list.

Claude.ai / Claude Desktop: Settings → Connectors → Add custom connector, then paste the URL.

Cursor (~/.cursor/mcp.json), Windsurf, or any client that takes a JSON block:

{
  "mcpServers": {
    "aeo-research": { "url": "https://aeo.advancelabs.dev/api/mcp/research/mcp" },
    "aeo-toolkit":  { "url": "https://aeo.advancelabs.dev/api/mcp/search/mcp" }
  }
}
Server Tools Credentials
aeo-research 12 None to connect. AEO audits and backlink research need nothing; citation checks take a Perplexity key per request.
aeo-toolkit 37 Sign in with your AEO Toolkit account: the client opens a browser on first use (in Claude Code, /mcp → Authenticate). Google, Bing and AI provider keys come from the account. Search Console, GA4, Bing, saved visibility checks, keyword volumes and backlink research. Legacy BYOK (a Google token as Authorization: Bearer, an optional x-bing-api-key) still works for the Search Console, GA4 and Bing tools.

Three things that trip people up:

  • The trailing /mcp is required. The bare /api/mcp/<slug> returns the adapter's own
    "Not found", which looks like a routing bug and is not.
  • Only aeo-toolkit has a login, and its discovery is path-scoped. It answers an anonymous
    request with a 401 pointing at /.well-known/oauth-protected-resource/api/mcp/search/mcp; its
    authorization server is /api/mcp/oauth. The ROOT /.well-known/oauth-* documents deliberately
    return 404, because aeo-research needs no login.
  • No tool edits your site. Every aeo-research tool is read-only. Five aeo-toolkit tools act
    on your account and are annotated as such: three visibility tools save checks to your dashboard
    (and use plan quota), and submit_indexnow and submit_to_bing submit URLs.

The research server replaced two servers on 2026-11-14: aeo-visibility (/api/mcp/ai-visibility/mcp)
and aeo-backlink (/api/mcp/backlink/mcp). Both URLs still work and serve their own tools, so
existing configs need no change.

The account server kept the search server's URL. /api/mcp/toolkit/mcp and /api/mcp/ga-gsc/mcp still work as
compatibility aliases; new configs should use /api/mcp/search/mcp.


Why AEO?

When a user asks ChatGPT "what is the best tool for X?", the answer comes from indexed content that AI models trust, not from ad-auction bidding. The trust signals for AI citation are:

  • Structured data (JSON-LD Organization, FAQPage, HowTo)
  • llms.txt: the AI equivalent of robots.txt
  • Canonical, server-rendered HTML: AI crawlers prefer static content
  • Topical authority: consistent, in-depth coverage of a topic

AEO Toolkit automates auditing all of these.


Monorepo Structure

aeo-toolkit/
├── packages/          # the six published libraries, plus shared config
├── apps/chrome-extension/
├── apps/docs/         # Astro + Starlight docs site (renders ../../docs)
├── docs/              # the documentation itself
└── brand/             # the mark, lockups, palette and type (brand/README.md)

Built with Turborepo · TypeScript 5 · Vitest · React 19


Design

The site is pixel art: a figure pushing a faceted sphere under a dithered dusk sky. Art is drawn
at a coarse cell, snapped to a small palette (ink, paper, two dusk oranges) with a 4x4 Bayer
ordered dither and scaled up with hard edges. Labels use Geist Pixel Square, headings and body
Geist Sans, code Geist Mono. Corners are square and shadows are hard-offset. The palette, type,
tokens and rules are in brand/README.md, with the assets
beside it. Anything a user sees should follow it, and
docs/CONVENTIONS.md says how in code.


Made by Advance Labs

Built and maintained by Advance Labs · All Advance Labs products

AEO Toolkit is built and maintained by Advance Labs Inc., a software studio building Creatin, Cartrix, and this toolkit.

This project dogfoods its own tooling: advancelabs.dev ships with llms.txt, JSON-LD Organization schema, SSG-rendered pages, and canonical URLs, all patterns the scoring engine teaches.


Code of Conduct

We follow the Contributor Covenant: be respectful and constructive in all project spaces, and report unacceptable behavior to [email protected].


© 2026 Advance Labs Inc. · advancelabs.dev

Yorumlar (0)

Sonuc bulunamadi