mcpField
A
AEO Audit

AEO Audit

Remote
github.com/piiiicoBusiness & Marketing0Updated 33w ago
Repository

About AEO Audit

AEO Audit is an MCP server that evaluates a website’s visibility in AI assistant answers and returns a score, issues and prioritized recommendations. It checks site content, metadata, structured data and technical signals.

Key features

  1. 01Score AI visibility from 0 to 100
  2. 02Inspect schema, metadata and content
  3. 03Check AI crawler access and signals
  4. 04List issues and ranked recommendations
  5. 05Provide a quick score and grade

Use cases

  1. 01Audit a business website for AI visibility
  2. 02Find site issues affecting AI discovery
  3. 03Check whether AI crawlers are blocked
  4. 04Prioritize changes to improve readiness

MCP support

The Streamable HTTP MCP endpoint exposes tools for full audits, quick scores and AI-readiness checks. It requires no authentication.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://aeo-mcp-server.amdal-dev.workers.dev/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

4
ParameterTypeRequiredDescription
domainstringYesThe domain to audit (e.g., 'example.com')
queriesarrayYesSearch queries to test
providerenumNoAI engine (default: exa)exa | perplexity
competitorsarrayNoCompetitor domains

Details

From the project README

AEO Audit MCP Server

AEO (Answer Engine Optimization) audit tool — check any website's AI visibility score and get actionable recommendations.

Live endpoint: https://aeo-mcp-server.amdal-dev.workers.dev/mcp Protocol: MCP Streamable HTTP (2025-03-26) Free to use — no auth required

What it does

Analyzes why businesses don't appear in ChatGPT, Claude, Perplexity, and other AI assistant answers. Returns:

  • Score 0-100 with letter grade (A–F)
  • Breakdown: schema markup, meta tags, content quality, technical config, AI signals
  • Issues: specific problems blocking AI visibility
  • Recommendations: prioritized action list

Tools

analyze_aeo(url)

Full audit. Returns score, grade, category breakdown, all issues, and ranked recommendations.

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "analyze_aeo",
    "arguments": { "url": "https://example.com" }
  }
}
get_aeo_score(url)

Quick check — score and grade only.

check_ai_readiness(url)

Checks if AI crawlers (GPTBot, ClaudeBot) are blocked, if /llms.txt exists, and other crawler access signals.

Usage with Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "aeo-audit": {
      "url": "https://aeo-mcp-server.amdal-dev.workers.dev/mcp",
      "type": "streamable-http"
    }
  }
}

Usage with Cursor / other MCP clients

Endpoint: https://aeo-mcp-server.amdal-dev.workers.dev/mcp Transport: Streamable HTTP (POST)

What AEO checks

  • Structured data (JSON-LD schema): LocalBusiness, FAQPage, AggregateRating, OpeningHours
  • Meta tags: Title, description, OpenGraph
  • Content quality: Word count, H1/H2 headings, location signals, FAQ section, prices
  • Technical: robots.txt AI bot access, llms.txt, sitemap, load speed
  • AI signals: Speakable schema, statistics/numbers, structured content

About

Built by Synlig Digital — AEO services for Norwegian businesses. Contact: [email protected]

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.