AEO Scanner — MCP Server
AI search visibility audit for any website. Two scores, one scan.
What it does
- AEO Score (0-100): How well AI search engines (ChatGPT, Perplexity, Google AI Overviews) can find, read, and cite your content
- Agent Readiness (0-100): How easily AI agents can understand, interact with, and transact on your site
Quick start
Remote server (recommended) — zero install, just add the URL:
# Claude Code
claude mcp add --transport http aeo-scanner https://aeo-mcp.convrgent.ai/mcp
# Claude Desktop / Claude.ai
# Settings → Connectors → Add custom connector → https://aeo-mcp.convrgent.ai/mcp
# Cursor — add to .cursor/mcp.json
{ "aeo-scanner": { "url": "https://aeo-mcp.convrgent.ai/mcp" } }
Then ask your AI assistant: "Scan example.com for AI visibility"
Alternative: local install via PyPI (stdio transport):
claude mcp add aeo-scanner -- uvx aeo-scanner
Tools
| Tool | What it does | Price |
|---|---|---|
scan_site | Quick dual-score scan + top issues | Free |
audit_site | Full 25+ check breakdown across 8 categories | $1.00 |
fix_site | Generated fix code — apply directly with Claude Code | $5.00 |
Free tier
scan_site works without any authentication. No API key, no wallet, no setup.
Rate limits: 20 scans/hour per IP, 5 per URL per day.
Paid tools
audit_site and fix_site require an API key:
- Get your key at scan.convrgent.ai
- Set
AEO_API_KEYin your MCP config
Or pay per call with USDC via x402 protocol (Base network).
Workflow
The included optimize_site prompt guides the full workflow:
- Scan — get baseline scores (free)
- Audit — see detailed breakdown by category ($1)
- Fix — get working code to apply ($5)
- Rescan — verify improvement (free)
Scoring
25+ checks across 8 categories. See the built-in aeo://reference/scoring-methodology resource for full details, or read scoring-methodology.md.
AEO categories: Structured Data (30%), Meta & Technical (20%), AI Accessibility (25%), Content Quality (25%)
Agent Readiness categories: Machine Identity (25%), API Discoverability (25%), Structured Actions (20%), Programmatic Access (20%), Data Clarity (10%)
Grades: A (90+), B (75-89), C (60-74), D (40-59), F (0-39)
Built by Convrgent — personality intelligence and AI visibility tools for agents.