Skip to main content
Glama
AdevAarons

Specularis AI Visibility Audit

by AdevAarons
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Hybrid

Specularis AI Visibility Audit — MCP Server

Run a free AI visibility (GEO/AEO) audit on any website from inside Claude, ChatGPT, or any MCP client — 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):

https://specularis-mcp-audit-production.up.railway.app/mcp

No installation needed — it's a remote MCP server. Add the URL above and you're done.

Connect it

Claude (claude.ai or Claude Desktop): Settings → Connectors → Add custom connector → paste the URL above.

Claude Code:

claude mcp add --transport http specularis-audit https://specularis-mcp-audit-production.up.railway.app/mcp

Then in any chat: "Audit example.com for AI visibility" — the tool runs.

Related MCP server: SEO/AEO Audit MCP

Tools

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 — a 0–100 AI-visibility score across 5 pillars, delivered as a PDF report.

book_strategy_call()

Returns a link to book a strategy call with Specularis.

What the full audit measures

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 — 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.

Who's behind it

Built by Specularis — a GEO/AEO agency helping businesses get found and cited by AI engines. The audit is free; the report is the real deliverable.

Self-hosting

The server is a single-file Node app (Streamable HTTP transport).

npm install
npm start

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.

License

MIT

This server cannot be deployed

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Maintenance

ActivityActive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • geo-audit

    nycsav
    A
    license
    Not graded
    quality
    C
    maintenance
    Evaluates any website's AI visibility with 15 checks across crawlability, structure, content, and connectivity, and provides actionable fixes.
    3
    MIT

  • ai-search-audit

    d08m
    A
    license
    Not graded
    quality
    B
    maintenance
    Enables auditing AI search visibility: checks site readiness for AI crawlers and measures whether ChatGPT, Gemini, and Perplexity recommend your site, including verbatim answers and citation gap analysis.
    66
    4
    AGPL 3.0

  • AEO Scanner

    Convrgent
    A
    license
    A
    quality
    D
    maintenance
    Enables users to scan any website for AI search visibility, producing AEO, GEO, agent readiness, and mention-readiness scores along with AI identity and business profile insights. Paid tools extend this to competitive comparisons, detailed audits, and generated fixes.
    4
    1
    MIT