Skip to main content
Glama

Server Details

Markdown scrape, site map, page metadata, screenshots, web search and PDF to text. Pay per call

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

B3.4/5.0

Scored across 9 tools

Disambiguation4/5

Most tools target clearly distinct resources or actions: URL discovery, metadata, PDF text, pricing, web search, markdown scraping, and screenshots. The only mild overlap is scrape vs. scrape_lite, both converting URLs to markdown with different cost/quality expectations, and screenshot vs. screenshot_full, which are clearly distinguished by viewport vs. full-page output.

Naming Consistency3/5

The names are readable but follow mixed conventions: single nouns (metadata, pdf, quote), verbs (scrape, search), and suffixed variants (scrape_lite, screenshot_full). There is no consistent verb_noun or resource_action pattern across the set.

Tool Count5/5

Nine tools is well-scoped for a web scraping/extraction and payment-aware API surface. Each tool appears to earn its place, and the set avoids excessive fragmentation.

Completeness4/5

The surface covers core web extraction workflows: URL discovery, metadata, markdown scraping, PDF extraction, screenshots, web search, and pricing/quoting. Minor gaps like a dedicated crawl or raw HTML endpoint can likely be worked around using map plus scrape, but they are still notable omissions.

Available Tools

9 tools
mapMap a site: links + sitemap URLsAInspect

Same-site URLs found on the page plus sitemap URLs (robots.txt Sitemap lines or /sitemap.xml), deduped, up to limit (default 200, max 1000). Paid: map $0.001 USDC on Base via x402 (charged only on success). Unpaid calls return x402 payment requirements; retry with _meta["x402/payment"].

Inputs: url (required), limit.

metadataPage metadata (title, OG, JSON-LD)AInspect

Title, meta description, canonical, lang, OpenGraph and Twitter tags, and parsed JSON-LD blocks of an HTML page. Paid: metadata $0.001 USDC on Base via x402 (charged only on success). Unpaid calls return x402 payment requirements; retry with _meta["x402/payment"].

Inputs: url (required).

pdfPDF to textAInspect

A public PDF URL in, its text page by page out (up to 50 pages, 10 MB; text-based PDFs). Paid: $0.008 USDC on Base via x402 (charged only when text comes back). Unpaid calls return x402 payment requirements; retry with _meta["x402/payment"].

Inputs: url (required), pages.

quotePrice and availability (free)CInspect

Free. Our price for a tier, how many providers are healthy right now, estimated latency, and payment status.

Inputs: url (required), tier.

scrapeScrape a page to markdownAInspect

Page to clean markdown, routed to a healthy provider with automatic failover. Paid: $0.008 USDC on Base via x402 (charged only on success). Unpaid calls return x402 payment requirements; retry with _meta["x402/payment"].

Inputs: url (required).

scrape_liteScrape a page to markdown (lite)AInspect

URL to markdown: any public page as clean markdown, with failover (/v1/scrape/lite: $0.003 per page). Paid: $0.003 USDC on Base via x402 (charged only on success). Unpaid calls return x402 payment requirements; retry with _meta["x402/payment"].

Inputs: url (required).

screenshotScreenshot a page (PNG)AInspect

The visible part of a public page (1280x800 viewport, JavaScript rendered) as a base64 PNG in image_base64. Paid: $0.008 USDC on Base via x402 (charged only on success). Unpaid calls return x402 payment requirements; retry with _meta["x402/payment"].

Inputs: url (required).

screenshot_fullFull-page screenshot (PNG)AInspect

The whole scrollable page (JavaScript rendered) as a base64 PNG in image_base64. Paid: $0.012 USDC on Base via x402 (charged only on success). Unpaid calls return x402 payment requirements; retry with _meta["x402/payment"].

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
      B
      maintenance
      Gives AI assistants real-time access to web data with the ability to scrape any website, bypass anti-bot systems, extract structured data, and capture screenshots through enterprise-grade infrastructure.
      6
      356 npm
      15
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Gives an agent a real browser. Turns any url into clean markdown, takes a screenshot of a url, and converts a url or raw html to pdf. It runs javascript, so it works on pages that a plain fetch returns empty. Respects robots.txt and refuses sites that block automation instead of trying to defeat them. No signup and no api key to start: the first call mints a free trial key and hands it back.
      MIT
    • F
      license
      Not graded
      quality
      A
      maintenance
      Enables AI agents and MCP clients to fetch webpages and crawl sites, extract main content, and convert it into clean Markdown with preserved links for fast, token-efficient scraping.
      -
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources