Free AI visibility (GEO/AEO) audit: can ChatGPT, Claude and Perplexity find and cite your website?
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
π‘ Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Run a free AI visibility (GEO/AEO) audit on any website from inside Claude, ChatGPT, or any MCP client β checks whether ChatGPT, Claude & Perplexity can find and cite it, with an instant snapshot and an optional full scored PDF report.
Hosted endpoint (Streamable HTTP):
No installation needed β it's a remote MCP server. Add the URL above and you're done.
Claude (claude.ai or Claude Desktop): Settings β Connectors β Add custom connector β paste the URL above.
Claude Code:
Then in any chat: "Audit example.com for AI visibility" β the tool runs.
| Tool | What it does |
|---|---|
run_ai_visibility_audit(website_url, email?, name?, role?) | Instant in-chat snapshot: AI crawler access (GPTBot, ClaudeBot, PerplexityBot), schema markup, llms.txt, content signals. Include an email to receive the full scored audit β a 0β100 AI-visibility score across 5 pillars, delivered as a PDF report. |
book_strategy_call() | Returns a link to book a strategy call with Specularis. |
The full report scores 5 pillars (20 points each): AI crawler accessibility, structured data & entity clarity, content quality signals, off-site presence (the sources AI engines actually cite), and live AI-answer visibility β including real Perplexity queries to test whether AI recommends the business today.
Validated against 14 sites across 4 niches: businesses AI recommends average 64.5/100; businesses AI ignores average 44.7. Notably, 8 of 12 audited businesses were unknowingly blocking AI crawlers at the network level.
Built by Specularis β a GEO/AEO agency helping businesses get found and cited by AI engines. The audit is free; the report is the real deliverable.
The server is a single-file Node app (Streamable HTTP transport).
Environment variables:
| Variable | Purpose |
|---|---|
N8N_WEBHOOK_URL | Backend audit engine endpoint (the hosted version uses Specularis's audit pipeline) |
CONTACT_URL | Booking link returned by book_strategy_call |
AUDIT_URL | Web-form fallback link included in responses |
PORT | Listen port (default 3000) |
Point any MCP client at http://localhost:3000/mcp.
MIT
No reviews yet β be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/specularis-ai-visibility-audit)<a href="https://allmcps.com/mcp/specularis-ai-visibility-audit"><img src="https://allmcps.com/api/badge/specularis-ai-visibility-audit?style=directory" alt="Specularis AI Visibility Audit on AllMCPs" /></a>