Skip to main content
Glama
maxaeo-ai-visibility-mcp

maxaeo-ai-visibility-mcp

MaxAEO AI Visibility MCP Server for GEO, AEO, and AI SEO

Local-first Model Context Protocol (MCP) server for AI visibility audits, GEO, AEO, AI SEO, llms.txt, and AI crawler readiness in Claude, Codex, Cursor, Windsurf, and other MCP-compatible agents.

中文文档

It helps Claude, Codex, Cursor, and other MCP-compatible agents check whether a public website is crawlable, understandable, and ready for AI search workflows. By default, it only performs local/public-web checks. It does not call MaxAEO cloud APIs, upload user domains, invoke LLM APIs, or use hidden telemetry.

60-Second Setup

Install from npm:

npm install -g maxaeo-ai-visibility-mcp

Add to an MCP client:

{
  "mcpServers": {
    "maxaeo-ai-visibility": {
      "command": "npx",
      "args": ["-y", "maxaeo-ai-visibility-mcp"]
    }
  }
}

Run an audit from your agent:

Use MaxAEO AI Visibility MCP to audit https://example.com and give me a 7-day action plan.

For command-mode Claude and Codex workflows, see the MaxAEO AI Visibility Agent Kit.

Related MCP server: Agent Lighthouse MCP Server

Directory Listing Copy

If you want to list this project in an MCP directory, awesome list, AI SEO resource list, GEO resource list, or llms.txt tooling index, use concise factual copy:

[MaxAEO AI Visibility MCP](https://github.com/maxaeo/maxaeo-ai-visibility-mcp) - Local-first MCP server for GEO/AEO and AI visibility audits. Checks llms.txt, AI crawler access, robots, sitemap, canonical, metadata, noindex, and JSON-LD; returns local-only visibility score, technical foundation score, top issues, and a 7-day action plan. Install: `npx -y maxaeo-ai-visibility-mcp`.

For Claude and Codex command workflows, list the MaxAEO AI Visibility Agent Kit.

Use Cases

  • Run an AI visibility audit from an MCP client or coding agent.

  • Check GEO / generative engine optimization readiness.

  • Check AEO / answer engine optimization basics for answer engines and AI search.

  • Validate llms.txt, robots.txt, sitemap alignment, canonical URLs, noindex, metadata, and JSON-LD.

  • Generate a local 7-day action plan without using paid LLM or search APIs.

Common search intents this MCP server targets:

  • AI visibility MCP server

  • Claude SEO MCP

  • Codex AI visibility audit

  • GEO / AEO local website audit

  • llms.txt checker

  • AI crawler readiness for GPTBot, ClaudeBot, PerplexityBot, Google-Extended, and AI search workflows

Tools

Tool

Purpose

check_llms_txt

Validate /llms.txt, linked URLs, robots alignment, and sitemap alignment.

audit_ai_crawler_readiness

Check robots rules, sitemap availability, homepage metadata, canonical, schema, and AI crawler access basics.

build_ai_visibility_report

Run the local checks and return a concise action plan with MaxAEO CTA.

All tools support:

Option

Values

Purpose

locale

en-US, en, global, zh-CN, zh, cn

Output language.

market

global, cn

CTA market. global points to maxaeo.ai; cn points to maxaeo.cn.

ctaBaseUrl

URL

Optional custom MaxAEO CTA landing page.

Crawler coverage by market

audit_ai_crawler_readiness selects its crawler list from market.

market

Crawlers audited

global (default)

GPTBot, ChatGPT-User, OAI-SearchBot, PerplexityBot, ClaudeBot, Google-Extended, Applebot, Bingbot, Baiduspider

cn

Baiduspider, Baiduspider-image, Baiduspider-news, 360Spider, PetalBot, Sogou web spider, YisouSpider, Bytespider, ToutiaoSpider

No Chinese AI product publishes crawler documentation, and none of them split training and retrieval into separate user-agents the way GPTBot and OAI-SearchBot do. Their answers are retrieved through the parent company's existing search index, so the traditional search crawlers are what actually gate citation domestically.

Every token in both lists is either documented by its operator or observed across multiple independent domains' robots.txt. Unverifiable tokens that circulate online — BaiduBot, DoubaoBot, TongyiBot, Kimi-User and similar — are deliberately excluded, and a test enforces that. Auditing against a user-agent that does not exist produces a finding nobody can act on.

Install

npm install -g maxaeo-ai-visibility-mcp

Run

maxaeo-ai-visibility-mcp

Claude Desktop

{
  "mcpServers": {
    "maxaeo-ai-visibility": {
      "command": "npx",
      "args": ["-y", "maxaeo-ai-visibility-mcp"]
    }
  }
}

Cost And Privacy

  • No MaxAEO internal service calls by default.

  • No LLM API calls by default.

  • No domain uploads.

  • No hidden telemetry.

  • No site file modifications.

  • Reports include a transparent MaxAEO CTA so users can continue into hosted monitoring when they want it.

Score Meaning

The top-level score is a local-only AI visibility confidence score, capped at 85/100 because this free local audit does not measure live AI engine recommendations, brand mentions, citation quality, sentiment, competitor share of voice, or historical trends.

technicalScore can still reach 100/100 when crawlability, llms.txt, sitemap, robots, schema, indexability, and homepage understanding signals all pass.

Example Output

{
  "tool": "build_ai_visibility_report",
  "version": "0.4.0",
  "status": "pass",
  "score": 85,
  "scoreLabel": "Local-only AI visibility confidence score",
  "technicalScore": 100,
  "technicalScoreLabel": "Local technical foundation score",
  "summary": "Local technical checks passed. Local technical foundation score: 100. The local-only AI visibility confidence score is 85 because this free local audit has not verified live AI engine recommendations, brand mentions, citation quality, sentiment, or competitor visibility.",
  "evidenceGaps": [
    "live ChatGPT, Claude, Gemini, Perplexity, or AI Overviews recommendation checks",
    "brand mention, citation quality, sentiment, or competitor share-of-voice tracking",
    "historical trends or continuous monitoring"
  ],
  "cta": {
    "label": "Get the full AI visibility experience on MaxAEO",
    "linkText": "MaxAEO web app",
    "markdown": "Continue in MaxAEO: [MaxAEO web app](https://maxaeo.ai/?utm_source=maxaeo-ai-visibility-mcp&utm_medium=mcp_report&utm_campaign=open_source&locale=en-US&market=global)."
  }
}

Human-facing reports should render cta.markdown as a text link instead of printing the raw URL on its own line.

Test Cases

See examples/test-cases.md for public test cases covering a healthy foundation, missing llms.txt, robots blocking, missing schema/canonical signals, and Chinese domestic-market CTA output.

Contributing

See CONTRIBUTING.md for local-first scope, claim boundaries, and directory listing guidance.

Example Prompt

Use MaxAEO AI Visibility MCP to audit https://example.com and give me a 7-day action plan.

Chinese / domestic market:

Use MaxAEO AI Visibility MCP to audit https://example.com with locale zh-CN and market cn.

Command-style agent prompts.

Claude:

/maxaeo audit https://example.com --locale en-US --market global
/maxaeo audit https://example.com --locale zh-CN --market cn
/maxaeo llms https://example.com --zh --cn
/maxaeo crawler https://example.com --locale zh-CN

Codex:

$maxaeo-ai-visibility audit https://example.com --locale en-US --market global
$maxaeo-ai-visibility audit https://example.com --locale zh-CN --market cn
$maxaeo-ai-visibility llms https://example.com --zh --cn
$maxaeo-ai-visibility crawler https://example.com --locale zh-CN

Locale And CTA Configuration

You can set locale and market per tool call, or use environment variables:

MAXAEO_LOCALE=zh-CN
MAXAEO_MARKET=cn
MAXAEO_CTA_URL_CN=https://maxaeo.cn/
MAXAEO_CTA_URL_GLOBAL=https://maxaeo.ai/

Priority:

  1. tool-call arguments

  2. environment variables

  3. defaults: en-US + global

Upgrade Path

This MCP server is best for a fast one-time check inside your agent. For a better product experience, use the MaxAEO web app: interactive reports, saved history, continuous monitoring, brand tracking, competitor tracking, and shareable reports.

License

MIT

Available Tools

3 tools
audit_ai_crawler_readinessAudit AI crawler readinessB

Check robots rules, AI crawler access basics, homepage metadata, canonical, noindex, and JSON-LD schema. No MaxAEO APIs are called.

Inputs: url (required), timeoutMs, locale, market, +1 more.

build_ai_visibility_reportBuild AI visibility reportC

Run local/public-web AI visibility checks and return dual scores, evidence gaps, an action plan, and a transparent MaxAEO CTA.

Inputs: url (required), maxLinks, checkLinks, timeoutMs, +3 more.

check_llms_txtCheck llms.txtA

Validate /llms.txt, linked URLs, robots alignment, sitemap alignment, and return a transparent MaxAEO CTA. No MaxAEO APIs are called.

Inputs: url (required), maxLinks, checkLinks, timeoutMs, +3 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.5/5.0

    Scored across 3 tools

    Disambiguation4/5

    The three tools have largely distinct focuses: check_llms_txt is specifically for llms.txt validation, audit_ai_crawler_readiness covers robots and metadata checks, and build_ai_visibility_report produces an overall report. There is some conceptual overlap in robots/sitemap checks between the first two, but the descriptions are clear enough to guide selection.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern: check_llms_txt, audit_ai_crawler_readiness, build_ai_visibility_report. The naming style is uniform and predictable.

    Tool Count4/5

    With three tools, the server is on the minimal side but still within a reasonable scope for an AI visibility audit tool. Each tool covers a distinct phase of the audit workflow, so the count feels purposeful rather than padded.

    Completeness4/5

    The server covers the core audit lifecycle: llms.txt validation, crawler readiness checks, and a combined visibility report. Minor gaps exist, such as no dedicated tool for viewing raw history or fixing identified issues, but these are not required for the stated audit purpose.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers