SmartFetch
Server Details
HTML/PDF/Markdown, browser render, screenshots, site intel, URL map & batch via Base/Solana x402.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- Friezaaaa/smartfetch
- GitHub Stars
- 0
- Server Listing
- SmartFetch
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 8 tools
Each tool has a recognizable role, and descriptions explicitly route agents (default fetch vs. token-saving text/markdown vs. forced rendering). Minor overlap remains because fetch_webpage already returns Markdown, text, links, and metadata, so agents may hesitate between it and the format-specific converters.
All tools use snake_case with clear resource-oriented names, mostly following a verb_noun pattern. webpage_to_markdown breaks the verb_noun convention, and batch_fetch_webpages pluralizes the resource while others are singular.
Eight tools is well-scoped for a webpage fetching and inspection server. Each tool covers a distinct capability—single fetch, batch fetch, text extraction, Markdown conversion, forced rendering, screenshots, site mapping, and SEO inspection—without obvious redundancy.
The surface covers fetching, multiple output formats, JavaScript rendering, screenshots, site mapping, and structured metadata/SEO inspection. Minor gaps include no authenticated or cookie-based fetching and no depth-limited crawling beyond URL discovery, but core workflows are well served.
Available Tools
8 toolsbatch_fetch_webpagesAInspect
Parallel batch webpage and document retrieval tool. Fetches up to 5 public URLs concurrently with fair settlement (returns 502 without settling if all fail), VPS browser concurrency protection, and native Markdown/plain text output.
Inputs: urls (required), no_cache, render_mode, max_chars_per_url.
extract_webpage_textAInspect
Token-efficient extractor that returns ONLY clean plain text and core metadata from a public webpage or PDF (omits Markdown formatting, links array, and raw HTML). Use when you only need plain readable text.
Inputs: url (required), max_chars, force_browser, only_main_content.
fetch_webpageAInspect
Primary webpage and PDF retrieval tool. Use by default to fetch any public HTTP/HTTPS webpage or PDF and return clean text, Markdown, links, and metadata. Uses fast HTTP first and automatically falls back to an isolated headless browser for JavaScript-rendered pages. (Use webpage_to_markdown or extract_webpage_text for token-saving single-format output, or render_webpage when you need raw rendered HTML DOM.)
Inputs: url (required), scroll, wait_ms, max_chars, +4 more.
inspect_webpageBInspect
Structured webpage and site intelligence and SEO inspection tool for any public URL. Extracts comprehensive metadata, OpenGraph, Twitter cards, JSON-LD schemas, contact details (emails, phones, social links), tech stack detection, security headers, and document outline.
Inputs: url (required), deep, render_mode, force_browser.
map_websiteAInspect
Website URL discovery and sitemap mapper. Discovers and maps internal URLs across a website using robots.txt, XML sitemaps (including nested sitemap indexes), and HTML links, with optional search filtering and subdomain support.
Inputs: url (required), search, max_urls, no_cache, +1 more.
render_webpageAInspect
Forced headless Chromium browser renderer for JavaScript-heavy SPAs and dynamic webpages. Always executes Tier 3 isolated browser rendering and returns the post-JS rendered HTML DOM alongside extracted text, Markdown, links, and metadata. Do not use for PDFs or static pages (use fetch_webpage instead).
Inputs: url (required), scroll, wait_ms, max_chars, +3 more.
screenshot_webpageBInspect
Browser-based webpage screenshot capture tool. Captures high-resolution JPEG or PNG screenshots of public webpages using isolated headless Chromium with configurable desktop/mobile viewport and optional full-page capture.
Inputs: url (required), scroll, wait_ms, viewport, +4 more.
webpage_to_markdownAInspect
Token-efficient converter that returns ONLY clean Markdown and core metadata from a public webpage or PDF (omits duplicate plain text, links array, and raw HTML). Use when you only need Markdown.
Inputs: url (required), max_chars, force_browser, only_main_content.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Pay-per-call web extract, DNS/WHOIS/IP lookup, PDF/RSS/sitemap tools. x402 USDC on Base/Algorand.
Screenshot, extract or audit any URL. Paid per call in USDC over x402; free tools need no wallet.
The web capability layer for AI agents: render, extract, DNS, SSL, WHOIS & more via x402.
$0.001/read URL-to-Markdown via x402 on Base. Settle-proven end-to-end 2026-11-02 (SELF-PROOF).
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceEnables agents to read any web page or document as markdown, html, links, screenshots or extracted JSON, map and crawl entire sites, and drive a persistent browser session that stays open between calls so pages can be inspected and clicked without reloading. Callers pay per request with a wallet over x402 — no API key or signup — and every route answers its own free GET with the fields it expects.1-
- AlicenseNot gradedqualityCmaintenanceCaptures full-page screenshots and PDFs from any URL using Chromium rendering, with pay-per-call via x402 micropayments.MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to call pay-per-use web tools over Streamable HTTP—converting URLs to Markdown, extracting metadata and links, checking URL status, DNS, email domains, WHOIS, robots.txt, and generating domain reports—with per-call USDC payments on Base via x402 and no API keys.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to capture web pages as PNG screenshots or PDF documents, with customizable dimensions and formats, using x402 micropayments on Base Mainnet.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.