Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

SmartFetch

REMOTE · SMARTFETCH-PRODUCTION-EA53.UP.RAILWAY.APP

HTML/PDF/Markdown, browser render, screenshots, site intel, URL map & batch via Base/Solana x402.

+53 this week 76 Trust /100

Last scanned (15 hours ago)

Scores higher than 65% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Web Scraping

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security57
Transport & Reachability100
Schema Quality & AI Usability62
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 2061 tokens (~171/item across 12 items; 12 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 12 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (12)

  • TLS certificate
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (1)

These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Authorization in Endpoint SecurityAuthorisation not fully verified: no authorisation is required to call this server, and 12 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 19 Nov 26 −1
    • Tool “batch_fetch_webpages” rewrote its description, which is the text the model reads security
    • Tool “extract_webpage_text” rewrote its description, which is the text the model reads security
    • Tool “fetch_webpage” rewrote its description, which is the text the model reads security
    • Tool “inspect_webpage” rewrote its description, which is the text the model reads security
    • Tool “map_website” rewrote its description, which is the text the model reads security
    • Tool “render_webpage” rewrote its description, which is the text the model reads security
    • Tool “screenshot_webpage” rewrote its description, which is the text the model reads security
    • Tool “search_and_fetch” rewrote its description, which is the text the model reads security
    • Tool “search_leads” rewrote its description, which is the text the model reads security
    • Tool “search_web” rewrote its description, which is the text the model reads security
    • Tool “search_x_posts” rewrote its description, which is the text the model reads security
    • Tool “webpage_to_markdown” rewrote its description, which is the text the model reads security
    • Schema quality: 150 → 171 ▼ functional
    • “inspect_webpage” added an optional parameter “urls” cosmetic
    • “screenshot_webpage” added an optional parameter “mobile” cosmetic
    • “inspect_webpage” made “url” optional cosmetic
  • 18 Nov 26 −1
    • Schema quality: 118 → 150 ▼ functional
    • Schema quality: 831 → 960 ▼ functional
    • Server version: 1.14.0 → 1.15.0 functional
    • New tool “search_and_fetch” functional
    • New tool “search_leads” functional
    • New tool “search_web” functional
    • New tool “search_x_posts” functional
    • New tool “map_website” functional
    • “extract_webpage_text” added an optional parameter “only_main_content” cosmetic
    • “fetch_webpage” added an optional parameter “dismiss_cookies” cosmetic
    • “fetch_webpage” added an optional parameter “only_main_content” cosmetic
    • “fetch_webpage” added an optional parameter “scroll” cosmetic
    • “fetch_webpage” added an optional parameter “wait_for_selector” cosmetic
    • “fetch_webpage” added an optional parameter “wait_ms” cosmetic
    • “inspect_webpage” added an optional parameter “deep” cosmetic
    • “render_webpage” added an optional parameter “dismiss_cookies” cosmetic
    • “render_webpage” added an optional parameter “only_main_content” cosmetic
    • “render_webpage” added an optional parameter “scroll” cosmetic
    • “render_webpage” added an optional parameter “wait_for_selector” cosmetic
    • “render_webpage” added an optional parameter “wait_ms” cosmetic
    • “screenshot_webpage” added an optional parameter “dismiss_cookies” cosmetic
    • “screenshot_webpage” added an optional parameter “scroll” cosmetic
    • “screenshot_webpage” added an optional parameter “wait_for_selector” cosmetic
    • “screenshot_webpage” added an optional parameter “wait_ms” cosmetic
    • “webpage_to_markdown” added an optional parameter “only_main_content” cosmetic
  • 17 Nov 26 +6
    • Schema quality: pass → fail ▼ functional
    • Tool coverage: 0% → 100% ▲ functional
    • Schema quality: fair → good functional
    • This server's schema is too large to store in full, so we cannot compare its tools day to day functional
  • 16 Nov 26 +49
    • Injection markers: unverified → pass ▲ security
    • Stability: unverified → pass ▲ security
    • Transport: fail → pass ▲ security
    • Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 4 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. security
    • Schema quality: 44 → 55 ▼ functional
    • Endpoint reachability: not serving MCP → reachable ▲ functional
    • Tool coverage: unverified → 100 ▲ functional
    • MCP protocol: unverified → pass ▲ functional
    • Schema quality: poor → fair functional
    • This server's schema is too large to store in full, so we cannot compare its tools day to day functional
  • 7 Nov 26 0
    • Endpoint reachability: unreachable → not serving MCP ▼ security
  • 6 Nov 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 4 Nov 26 0
    • Endpoint reachability: not serving MCP → unreachable ▼ security
    • HSTS header: fail → unverified ▼ security
    • TLS certificate: pass → unverified ▼ security
    • Transport: Transport check failed: declared streamable-http, but we couldn't connect to verify it. security
  • 31 Oct 26 −46
    • Endpoint reachability: reachable → not serving MCP ▼ security
    • Stability: pass → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • Transport: pass → fail ▼ security
    • Authorization: Authorisation not yet verified: we couldn't confirm whether this endpoint requires it. security
    • Capabilities: pass → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://smartfetch-production-ea53.up.railway.app/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=*.up.railway.app CN=YE2,O=Let's Encrypt,C=US 27 Sept 2026 26 Dec 2026 ECDSA 256 ECDSA-SHA384 618edc56941aa1165ddb080bf9f799eb7c1
SANs: *.up.railway.app, up.railway.app
CN=YE2,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 4df3b15dd6c0784c507cd37b58e6f115
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of smartfetch-production-ea53.up.railway.app. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
app. DS published 23684 8 Verified
railway.app. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
x-content-type-options nosniff

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://smartfetch-production-ea53.up.railway.app/mcp Verified 200
http (plaintext) http://smartfetch-production-ea53.up.railway.app/mcp HTTPS enforced 301 https://smartfetch-production-ea53.up.railway.app/mcp
MCP tools · 12 exposed · ~2,061 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
batch_fetch_webpages ~168

Parallel batch webpage and PDF document extraction tool (pdf, pdf-to-markdown, pdf text extraction, pdf ocr alternative, whitepaper, rfc, academic paper, spa, anti-bot, stealth chromium). Fetches up to 5 public URLs concurrently with Markdown, fenced code blocks, OpenGraph metadata, JSON-LD, pricing tables, and fair settlement (502 if all fail).

NameTypeReqDescription
max_chars_per_urlinteger–Maximum characters returned per URL.
no_cacheboolean–Bypass cache lookup.
render_modestring–Rendering strategy: 'auto' (fast HTTP with browser fallback capped at 2) or 'http_only'.
urlsarrayyesList of 1 to 5 public HTTP/HTTPS URLs to retrieve in parallel.

No output schema declared.

No examples provided.

extract_webpage_text ~118

Token-efficient PDF & webpage text extractor (pdf text extraction, pdf ocr alternative) returning clean plain text and metadata from any public webpage, whitepaper, or PDF.

NameTypeReqDescription
force_browserboolean–Start with browser rendering instead of fast HTTP retrieval.
max_charsinteger–Maximum characters returned for content.
only_main_contentboolean–Extract only main article/content (strips nav, footer, aside).
urlstringyesPublic HTTP or HTTPS URL of a webpage or PDF to extract plain text from.

No output schema declared.

No examples provided.

fetch_webpage ~289

Primary webpage and PDF retrieval tool & document extraction (pdf, pdf-to-markdown, pdf text extraction, pdf ocr alternative, whitepaper, rfc, academic paper). Extracts clean text, Markdown, fenced code blocks, pricing tables, OpenGraph metadata, JSON-LD, and links from any public HTTP/HTTPS webpage or PDF. Uses Chrome TLS fingerprint HTTP first and automatically escalates to stealth Chromium dynamic rendering for JavaScript hydration, SPA shells, Cloudflare bypass, WAF, and anti-bot 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.)

NameTypeReqDescription
dismiss_cookiesboolean–Attempt to dismiss cookie/GDPR banners before extraction.
force_browserboolean–Start with browser rendering instead of fast HTTP retrieval.
max_charsinteger–Maximum characters returned for content and Markdown.
only_main_contentboolean–Extract only main article/content (strips nav, footer, aside).
scrollboolean–Scroll down to trigger lazy-loaded content before extraction.
urlstringyesPublic HTTP or HTTPS URL of a webpage or PDF to retrieve.
wait_for_selector––Optional CSS selector to wait for before extraction.
wait_msinteger–Optional extra wait in milliseconds (0-5000) after page load.

No output schema declared.

No examples provided.

inspect_webpage ~204

Security audit, WHOIS, RDAP, DNS lookup (MX, SPF, DMARC), SSL/security headers (HSTS, CSP, X-Frame-Options), tech stack (Wappalyzer-style), and B2B company enrichment / email finder for 1 to 5 URLs (url or urls). Supports deep=true sub-crawling of /contact, /about, /pricing, and /team plus Google Workspace / Microsoft 365 detection.

NameTypeReqDescription
deepboolean–Sub-crawl /contact, /about, /pricing and gather DoH/RDAP domain intel.
force_browserboolean–Force browser rendering bypassing HTTP tier.
render_modestring–Rendering strategy: 'auto' (HTTP with browser escalation on SPA shell), 'http_only', or 'browser'.
url––Public HTTP or HTTPS URL of a webpage to inspect.
urls––Optional list of 1-5 public URLs to inspect concurrently.

No output schema declared.

No examples provided.

map_website ~138

Sitemap crawler, robots.txt parser, documentation URL mapper, and internal link discovery tool. Discovers up to 500 internal URLs from robots.txt, XML sitemaps (including nested sitemap indexes), and HTML links, with optional search filtering and subdomain support.

NameTypeReqDescription
include_subdomainsboolean–Include URLs on subdomains of the base domain.
max_urlsinteger–Maximum number of URLs returned (1 to 500).
no_cacheboolean–Bypass cache lookup.
search––Optional case-insensitive substring filter for discovered URLs.
urlstringyesPublic HTTP or HTTPS website URL to map.

No output schema declared.

No examples provided.

render_webpage ~197

Forced stealth headless Chromium renderer for any public webpage URL (JavaScript hydration, SPAs, Cloudflare/WAF anti-bot pages, and dynamic rendering). Returns post-JS rendered HTML DOM, Markdown, fenced code blocks, OpenGraph metadata, JSON-LD, and links.

NameTypeReqDescription
dismiss_cookiesboolean–Attempt to dismiss cookie/GDPR banners before extraction.
max_charsinteger–Maximum characters returned for content, Markdown, and HTML.
only_main_contentboolean–Extract only main article/content (strips nav, footer, aside).
scrollboolean–Scroll down to trigger lazy-loaded content before extraction.
urlstringyesPublic HTTP or HTTPS webpage URL for forced headless browser rendering.
wait_for_selector––Optional CSS selector to wait for before extraction.
wait_msinteger–Optional extra wait in milliseconds (0-5000) after page load.

No output schema declared.

No examples provided.

screenshot_webpage ~223

Desktop (1280x800) & mobile (390x844, mobile=true) responsive compliance screenshot, visual audit, phishing verification, and full-page webpage URL capture tool using isolated stealth Chromium.

NameTypeReqDescription
dismiss_cookiesboolean–Attempt to dismiss cookie/GDPR banners before capture.
full_pageboolean–Capture the full scrollable page height up to 4000px.
image_formatstring–Output image format ('jpeg' or 'png').
mobileboolean–Shortcut to capture mobile 390x844 responsive compliance viewport.
scrollboolean–Scroll down to trigger lazy-loaded content before capture.
urlstringyesPublic HTTP or HTTPS URL of a webpage to capture as a screenshot.
viewportstring–Device viewport preset ('desktop' for 1280x800, 'mobile' for 390x844).
wait_for_selector––Optional CSS selector to wait for before capture.
wait_msinteger–Optional extra wait in milliseconds (0-5000) before capture.

No output schema declared.

No examples provided.

search_and_fetch ~152

End-to-end RAG pipeline: real-time web search (SERP) plus parallel scraping of full article Markdown, fenced code blocks, OpenGraph metadata, and JSON-LD from top matching pages to corroborate sources.

NameTypeReqDescription
max_chars_per_pageinteger–Max characters per fetched page (1000-15000).
no_cacheboolean–Bypass cache lookup.
num_resultsinteger–Number of top URLs to fetch (1-5).
providerstring–Search provider: 'auto', 'serper', or 'exa'.
querystringyesSearch query string.
render_modestring–Render mode: 'auto' or 'http_only'.

No output schema declared.

No examples provided.

search_leads ~177

Local business leads & B2B outbound generator (Google Maps scraper, Google Places, med spa, cosmetic dentist, contractors). Discovers businesses and runs concurrent Deep /inspect to extract emails, phones, ratings, reviews, tech stack (WordPress, Shopify, HubSpot), and mail providers (Google Workspace, Microsoft 365).

NameTypeReqDescription
countrystring–Country code (default 'us').
deepboolean–Inspect /contact, /about, /pricing pages.
languagestring–Language code (default 'en').
max_leadsinteger–Maximum leads to enrich (1-5).
no_cacheboolean–Bypass cache lookup.
querystringyesB2B/local business search query.
sourcestring–Lead source: 'maps' or 'web'.

No output schema declared.

No examples provided.

search_web ~158

Real-time web search, Google News, and Google Places SERP API powered by Serper (with Exa fallback). Returns ranked titles, URLs, snippets, dates, and Places metadata to corroborate sources.

NameTypeReqDescription
countrystring–Country code (default 'us').
languagestring–Language code (default 'en').
no_cacheboolean–Bypass cache lookup.
num_resultsinteger–Number of results (1-10).
providerstring–Search provider: 'auto' (Serper first), 'serper', or 'exa'.
querystringyesSearch query string.
search_typestring–Search type: 'web', 'news', or 'places'.

No output schema declared.

No examples provided.

search_x_posts ~120

Live Twitter search & X posts API for social sentiment, developer sentiment, crypto alpha, trending topics, micropayments, and latest tweets. Returns engagement metrics, author handles, follower counts, and pagination cursor.

NameTypeReqDescription
cursor––Optional pagination cursor from previous response.
max_tweetsinteger–Maximum posts returned (1-20).
no_cacheboolean–Bypass cache lookup.
querystringyesX/Twitter advanced search query.
query_typestring–Sort order: 'Latest' or 'Top'.

No output schema declared.

No examples provided.

webpage_to_markdown ~117

Token-efficient PDF & webpage converter returning clean Markdown, fenced code blocks, pricing tables, and metadata from any public URL, PDF, whitepaper, RFC, or SPA.

NameTypeReqDescription
force_browserboolean–Start with browser rendering instead of fast HTTP retrieval.
max_charsinteger–Maximum characters returned for Markdown.
only_main_contentboolean–Extract only main article/content (strips nav, footer, aside).
urlstringyesPublic HTTP or HTTPS URL of a webpage or PDF to retrieve as Markdown.

No output schema declared.

No examples provided.

Install

How do I install the SmartFetch MCP server?

SmartFetch is a hosted endpoint at https://smartfetch-production-ea53.up.railway.app/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · smartfetch-production-ea53.up.railway.app

# add to Claude Code
claude mcp add --transport http friezaaaa-smartfetch 'https://smartfetch-production-ea53.up.railway.app/mcp'
Common questions

What is the SmartFetch MCP server?

SmartFetch is an MCP server listed in the public MCP registry as io.github.Friezaaaa/smartfetch. HTML/PDF/Markdown, browser render, screenshots, site intel, URL map & batch via Base/Solana x402. This page covers its hosted endpoint (https://smartfetch-production-ea53.up.railway.app/mcp).

Is the SmartFetch MCP server safe to use?

SmartFetch scores 76 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the SmartFetch MCP server expose?

SmartFetch exposes 12 tools: fetch_webpage, webpage_to_markdown, extract_webpage_text, render_webpage, screenshot_webpage, and 7 more. Their descriptions and schemas cost roughly 2,061 tokens of context every time the server is loaded.

Does the SmartFetch MCP server require authentication?

No. We connected to SmartFetch without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the SmartFetch MCP server still maintained?

SmartFetch is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the SmartFetch MCP server?

VerifyMCP ran 12 checks on SmartFetch, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about SmartFetch: Authorization. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.