Skip to main content
Glama

AI Site Scorer

Server Details

Check website AI-readiness: Schema.org, llms.txt, E-E-A-T, robots.txt. Works in Cursor & Claude.

If you are the author of this connector, you can claim ownership. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2024-11-05
URL
ChatGPT
–
Claude
–

TDQS

B3.4/5.0

Scored across 10 tools

Disambiguation2/5

analyze_url and scan_site both take a URL and return AI-readiness scores/fixes with the same access and pricing, so an agent cannot easily tell which to pick (scan_site is just "methodology v2"). Similarly, generate_fix_prompt and get_fix_plan (whose format option is literally "prompt") produce competing fix-oriented outputs, and enhance_report vs get_report require understanding report lifecycle state rather than a clear action boundary.

Naming Consistency5/5

All ten tools follow a uniform snake_case verb_noun pattern (analyze_url, get_report, list_signals, generate_fix_prompt, etc.). No mixed casing or stray conventions; the only oddity is semantic (analyze vs scan for the same resource), not structural.

Tool Count4/5

Ten tools is a well-scoped size for a scan-and-report pipeline. One slot is wasted on get_visibility, which is explicitly "Not available yet" and cannot be used, slightly inflating the surface.

Completeness4/5

The core lifecycle is covered: submit scan (two ways), fetch report by job ID, enhance, derive fix plan and IDE prompt, list history, and browse the signal registry. Gaps are minor — no cancel/delete or status-polling beyond wait_for_result, and visibility tracking is advertised but unimplemented.

Available Tools

10 tools
analyze_urlAInspect

Submit a URL for AI-readiness analysis. Checks how well the site is structured for AI/LLM crawling (robots.txt, structured data, page speed, content quality, etc.). Returns scores and recommendations. Set wait_for_result=true to wait for completion (up to 60s). Pricing: Free for registered users within fair-use limits; Pro subscription for high volume. Without an account (optional x402):$0.001 USDC for analysis only; $0.006 USDC combined when enhance=true ($0.001 analyze + $0.005 enhance, charged as a single upfront payment so only one X-PAYMENT header is needed per request).

Inputs: url (required), enhance, wait_for_result.

enhance_reportBInspect

Run LLM deep analysis on a completed report. Returns detailed AI analysis with priority issues and actionable recommendations. Pricing: Included with Pro subscription, or $0.005 USDC per request via x402 (no account or free plan).

Inputs: job_id (required).

generate_fix_promptBInspect

Generate a Cursor/IDE-ready prompt to fix AI readiness issues found in a report. Returns a comprehensive, actionable developer prompt. Pricing: Included with Pro subscription, or $0.002 USDC per request via x402 (no account or free plan).

Inputs: job_id (required).

get_fix_planAInspect

Get the fix plan of a scan: changes ordered by evidence level x ease, stop factors first, each with a ready snippet and a registry card. format: markdown (default), json or prompt (paste into Cursor / Claude Code).

Inputs: scan_id (required), format.

get_reportAInspect

Fetch a previously completed analysis report by job ID. Returns scores, check details, and recommendations.

Inputs: job_id (required).

get_signalBInspect

Get one registry signal card: evidence level, sources with dates, how it is measured, fix template. Free, no auth.

Inputs: signal_id (required).

get_visibilityCInspect

Visibility tracking of a project in AI answers (citations, share of voice). Not available yet.

Inputs: project_id.

list_recent_analysesAInspect

List the 10 most recent analyses for the authenticated account. Returns URLs, scores, and statuses.

Inputs: limit.

list_signalsAInspect

List GEO signals from the evidence registry: what helps AI search engines find and cite a site, each with an evidence level (A = experiment/official, B = large correlation, C = practice, X = no effect) and sources. Free, no auth.

Inputs: axis, level.

scan_siteBInspect

Scan a URL with methodology v2: three independent indices (access for AI search, content citability, agent readiness), stop factors and the top fixes ranked by evidence level. Same access/pricing as analyze_url.

Inputs: url (required).

Tool Schema Changelog

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

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      C
      maintenance
      Enables AI agents to check whether a public website is crawlable, understandable, and ready for AI search workflows through local-only audits of robots.txt, sitemaps, metadata, and llms.txt.
      3
      79 npm
      2
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Checks whether a website is readable and citable by AI search engines — llms.txt, Schema.org structured data, AI-bot access in robots.txt, content freshness, answer directness, E-E-A-T signals, plus a LocalBusiness Rich Results validator. Free, no API key, remote Streamable HTTP.
      1
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Checks a website's robots.txt and Cloudflare settings to identify AI crawler blocking. Also generates llms.txt content to improve visibility to AI answer engines.
      3
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources