Tools Reference - Glippy MCP Documentation

analyze_domain

Core

Run a comprehensive GEO readiness analysis on a domain. Checks robots.txt, llms.txt, homepage HTML (16 scoring categories), sitemap.xml, and security headers.

Parameters

Parameter	Type	Required	Description
`domain`	string	Yes	Domain to analyze (e.g., `"example.com"`). No https:// prefix.
`max_pages`	integer	No	Pages to crawl (1-10). Default: 10.
`render_mode`	enum	No	`"static"` (default), `"auto"` (static with Chrome fallback on bot-block), or `"chrome"` (always Chrome). See Render Modes.
`output_format`	enum	No	`"text"` (default) or `"json"`. Use JSON to pass results to export_report.

Example

Analyze example.com for GEO readiness

Returns

Overall GEO score (0-100) with letter grade
Page type detection (article, product, homepage, etc.)
16 category scores with pass/fail/warn checks
robots.txt analysis with AI crawler access
llms.txt presence and content preview
Sitemap discovery status

check_robots_txt

Check a domain's robots.txt specifically for AI crawler access rules. Reports which crawlers (GPTBot, ClaudeBot, etc.) are blocked or allowed.

Parameters

Parameter	Type	Required	Description
`domain`	string	Yes	Domain to check. No https:// prefix.

Example

Which AI crawlers are blocked on example.com?

AI Crawlers Detected

GPTBot, Google-Extended, CCBot, anthropic-ai, ClaudeBot, Bytespider, PerplexityBot, ChatGPT-User, AmazonBot, cohere-ai

check_llms_txt

Check if a domain has an llms.txt file — the emerging standard for providing context to LLMs about a site's purpose and content.

Parameters

Parameter	Type	Required	Description
`domain`	string	Yes	Domain to check. No https:// prefix.

Example

Does example.com have an llms.txt file?

get_geo_summary

Get a concise GEO readiness summary: overall score, grade, top 3 strengths, and top 3 issues. Use for quick assessments.

Parameters

Parameter	Type	Required	Description
`domain`	string	Yes	Domain to check. No https:// prefix.
`render_mode`	enum	No	`"static"` (default), `"auto"`, or `"chrome"`. See Render Modes.

Example

Give me a quick GEO summary of example.com

compare_domains

Pro

Analyze multiple domains in parallel and compare their GEO scores side by side. Perfect for competitive analysis.

Parameters

Parameter	Type	Required	Description
`domains`	array[string]	Yes	2-50 domains to compare. No https:// prefix. For more than 50, run multiple times and merge the results.
`max_pages`	integer	No	Pages per domain (1-10). Default: 10.
`render_mode`	enum	No	`"static"` (default), `"auto"`, or `"chrome"`. Applied per domain. See Render Modes.
`output_format`	enum	No	`"text"` (default) or `"json"`. Use JSON to pass results to export_bulk_report.

Example

Compare GEO scores: example.com, competitor1.com, competitor2.com

analyze_sitemap

Pro

Fetch a sitemap XML, extract URLs, and analyze each page. Supports regular sitemaps and sitemap index files.

Parameters

Parameter	Type	Required	Description
`sitemap_url`	string	Yes	Full URL to sitemap (e.g., `"https://example.com/sitemap.xml"`)
`max_urls`	integer	No	Max URLs to analyze (1-50,000). Default: all found.
`rate_limit`	number	No	Requests/second per domain (0.1-100). Default: 5.
`render_mode`	enum	No	`"static"` (default), `"auto"`, or `"chrome"`. Applied per URL. See Render Modes.
`output_format`	enum	No	`"text"` (default) or `"json"`. Use JSON to pass results to export_bulk_report.

Example

Analyze all pages in https://example.com/sitemap.xml

analyze_urls

Pro

Run GEO analysis on a specific list of URLs. URLs can span multiple domains.

Parameters

Parameter	Type	Required	Description
`urls`	array[string]	Yes	Full URLs to analyze (1-50,000). Include https://.
`rate_limit`	number	No	Requests/second per domain (0.1-100). Default: 5.
`render_mode`	enum	No	`"static"` (default), `"auto"`, or `"chrome"`. Applied per URL. See Render Modes.
`output_format`	enum	No	`"text"` (default) or `"json"`. Use JSON to pass results to export_bulk_report.

Example

Analyze these pages: https://example.com/about, https://example.com/pricing

export_report

Generate a styled, shareable report in Markdown or HTML format — matching the Glippy browser extension's export.

Parameters

Parameter	Type	Required	Description
`format`	enum	Yes	`"markdown"`, `"markdown_full"`, or `"html"`
`domain`	string	No*	Domain to analyze. No https:// prefix.
`max_pages`	integer	No	Pages to crawl (1-10). Default: 10. Ignored if analysis_result provided.
`render_mode`	enum	No	`"static"` (default), `"auto"`, or `"chrome"`. Ignored if analysis_result provided. See Render Modes.
`analysis_result`	object	No*	Pre-computed result from analyze_domain (with output_format='json').

*Provide either domain or analysis_result

Example

Generate an HTML report for example.com

export_bulk_report

Pro

Generate a styled report for bulk analysis: domain comparison, URL list, or sitemap crawl.

Parameters

Parameter	Type	Required	Description
`format`	enum	Yes	`"markdown"` or `"html"`
`domains`	array[string]	No*	Compare 2-50 domains. No https:// prefix.
`urls`	array[string]	No*	Analyze 1-50,000 URLs. Include https://.
`sitemap_url`	string	No*	Full URL to sitemap to crawl.
`analysis_results`	object	No*	Pre-computed results from compare_domains, analyze_urls, or analyze_sitemap (with output_format='json').
`max_pages`	integer	No	For domains: pages per domain (1-10). Default: 10.
`max_urls`	integer	No	For sitemap: max URLs to analyze (1-50,000).
`rate_limit`	number	No	Requests/second per domain (0.1-100). Default: 5.
`render_mode`	enum	No	`"static"` (default), `"auto"`, or `"chrome"`. Ignored if analysis_results provided. See Render Modes.

*Provide exactly one of: domains, urls, sitemap_url, or analysis_results

Example

Generate an HTML comparison report for example.com and competitor.com

Render Modes

Reference

Every analysis tool accepts a render_mode parameter controlling how HTML is fetched for scoring. Some sites (Cloudflare, Akamai, DataDome, PerimeterX, Incapsula) block plain Node fetches; Chrome-backed modes drive a real browser to get past them. Auditing your own site? The cleaner fix is to allow-list the GlippyBot User-Agent — see the GlippyBot allow-list guide.

Modes

Mode	Behavior	Use when
`static` (default)	Plain Node fetch. Fast, no Chrome needed.	Targets don't block bots, or you want the static-crawler view.
`auto`	Static first; retry via Chrome if the response looks bot-blocked (401/403/407/429/503 or empty 2xx).	Mixed workloads — most sites stay on the fast path, only blocked ones pay the Chrome cost. Recommended for competitive audits.
`chrome`	Every URL fetched via Chrome. Slowest, most resilient.	Target aggressively detects headless, or you want uniform Chrome rendering.

Result field

The returned analysis includes a renderMode field indicating which path ran:

Value	Meaning
`static`	Static fetch succeeded; Chrome not invoked.
`chrome`	Launched directly via Chrome (explicit mode).
`chrome-fallback`	Static fetch was blocked; Chrome recovered a 2xx.
`chrome-blocked-<code>`	Chrome was tried but also got blocked with the given status.
`static-blocked`	Static fetch failed and Chrome was unavailable or errored.

Chrome setup

Auto and chrome modes need a local Chrome/Chromium binary. The server auto-detects from CHROME_PATH, PUPPETEER_EXECUTABLE_PATH, or common install paths (Windows: C:\Program Files\Google\Chrome\Application\chrome.exe; macOS: /Applications/Google Chrome.app/Contents/MacOS/Google Chrome; Linux: /usr/bin/google-chrome). If none is found, render_mode: "static" continues to work; other modes will record static-blocked.

Attaching to your own Chrome

Sites that fingerprint the headless build can still block the server-launched browser. Launch a separate Chrome with remote debugging and have the server attach to it by setting CHROME_REMOTE_URL in the MCP server env:

# macOS
/Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome \
  --remote-debugging-port=9222 --user-data-dir=/tmp/glippy-chrome &

# Windows (PowerShell)
& "C:\Program Files\Google\Chrome\Application\chrome.exe" `
  --remote-debugging-port=9222 --user-data-dir=C:\Temp\glippy-chrome

# Linux
google-chrome --remote-debugging-port=9222 --user-data-dir=/tmp/glippy-chrome &

# Then in your MCP config env:
#   CHROME_REMOTE_URL=http://localhost:9222

Using a dedicated --user-data-dir keeps this session isolated from your normal browsing. When attached, the fetcher leaves UA/headers/stealth untouched so requests look identical to a human browsing from that profile.