MCP.Market

Browser Scraper MCP server

by eurafaeldecarvalho·io.github.eurafaeldecarvalho/browser-scraper·v0.8.3·11 stars
No reviews yet

Stealth Chrome for AI agents: bot-protected sites, Turnstile, closed Shadow DOM, clean Markdown.

A92/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Growing

11 stars57 downloads/wk

Reviews

Write one

Nobody has reviewed Browser Scraper yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Browser Scraper tools (13)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • check_egress

    Report the browser's exit IP, ASN/org, country and whether it looks like a datacenter (the #1 reason sites block). Useful before debugging blocks.

  • click

    Click an element by ref with human-like mouse movement. Returns the updated snapshot.

  • go_back

    Go back in history.

  • markdown

    Read the current page as clean Markdown (main content only by default; includes closed shadow DOM). Best for: articles, docs, product pages — far fewer tokens than a snapshot. Pass `query` to keep only the relevant sections.

  • metadata

    Structured metadata of the current page: title, description, canonical, OpenGraph, Twitter card and JSON-LD (schema.org: products, prices, articles…).

  • navigate

    Open a URL in the stealth browser and return the page snapshot (accessibility outline with [ref=…] on interactive elements). Best for: starting a browsing task, sites behind Cloudflare/bot checks. Not for: fetching many URLs in bulk (use scrape).

  • press_key

    Press a keyboard key on the focused element (e.g. Enter, Escape, Tab, ArrowDown).

  • scrape

    One-shot fetch of a URL as Markdown (+ metadata), escalating automatically: plain HTTP → stealth browser → browser with Turnstile solving. Best for: reading a page you don't need to interact with. Does not change the current tab.

  • screenshot

    PNG screenshot of the current page (viewport, or full page).

  • snapshot

    Accessibility snapshot of the current page: roles, names and [ref=…] for interactive elements, including elements inside closed shadow DOM and cross-origin iframes. Refs are valid until the next snapshot. Set interactiveOnly for a short list of what can be clicked/typed.

  • solve_turnstile

    Solve an interactive Cloudflare Turnstile checkbox on the current page with human-like input. Use when the snapshot shows a Cloudflare challenge.

  • type

    Type text into an element by ref with human-like keystrokes. Use {{SECRET_NAME}} placeholders for credentials configured on the server — never ask the user for raw secrets. Set submit to press Enter afterwards.

  • wait

    Wait for a number of seconds (max 30), e.g. for a slow page or a challenge to clear. Returns the snapshot.

Public scan report

scanner v0.1.10 · 2026-10-28 · same rubric, same numbers if you re-run it

no findings
  • Code scan54 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Browser Scraper compares

Against every graded Scraping and browsing MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
92/100
higher than 85% of 868 Scraping and browsing servers
Tools
13
the typical Scraping and browsing server has 6
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
11
more than 81% of 581 Scraping and browsing servers
Downloads a week
57
more than 44% of 304 Scraping and browsing servers with a package

What its tools let an agent do: 12 read · 1 change

Release history: 2 versions in the registry since 2026-10-18, latest 2026-10-27, typically one every 9 days.

Install Browser Scraper in Claude Code, Cursor or VS Code

Runs npx -y @eurafaeldecarvalho/browser-scraper on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add browser-scraper -- npx -y @eurafaeldecarvalho/browser-scraper
Add to Cursor

What the publisher says

From the Browser Scraper repository's README, as published. We do not edit it. Read it on GitHub

Browser Scraper: the stealth browser for web scraping and AI agents

Undetected Chrome for Node.js that reads and operates the sites that block bots. Use it as a library, a CLI or an MCP server for Claude, Cursor and Codex. It turns any page, including closed Shadow DOM and cross-origin iframes, into clean Markdown, structured data or an accessibility snapshot an agent can click through. Local, free, MIT, bring-your-own-LLM.

CreepJS: 0% headless, 0% stealth · bot.sannysoft.com: 0 failures · no Runtime.enable leak (what that means, and where it stops)

Recorded on one desktop PC: the Turnstile test page at nowsecure.nl in headless mode, bot.sannysoft.com headful on the PC's own GPU.

import { scrape } from "@eurafaeldecarvalho/browser-scraper";

const page = await scrape({ url: "https://example.com", formats: ["markdown", "metadata"] });
console.log(page.tier);     // "http" | "browser" | "stealth": the cheapest tier that worked
console.log(page.markdown); // clean, LLM-ready Markdown of the main content
# Give Claude Code a browser that gets through Cloudflare:
claude mcp add browser-scraper -- npx -y @eurafaeldecarvalho/browser-scraper mcp

@eurafaeldecarvalho/browser-scraper drives real Chrome over the raw DevTools Protocol (CDP). It never sends Runtime.enable, one of the most widely fingerprinted automation signals, and every layer of the browser's identity tells the same story. On top of that stealth core it adds the pieces AI workloads need: Markdown and metadata extraction, an accessibility snapshot with clickable refs, a one-call scrape() that escalates from plain HTTP to a stealth browser only when it has to, an MCP server, and optional LLM extraction with any model.

Why this one:

  • Gets through where headless browsers get blocked. There is no Runtime.enable leak, the persona (UA, Client Hints, WebGL, timezone, locale) is coherent, and mouse and keyboard input are human-like. solveTurnstile() handles Cloudflare's checkbox.
  • Sees everything. find(), markdown() and snapshot() all reach into closed shadow roots and cross-origin iframes, which Playwright's snapshot and Readability-style extractors miss.
  • Built for agents. The MCP server and CLI work with no extra install. Credentials are typed through {{SECRET}} placeholders so the model never sees them, an allow-list restricts domains, and page content is fenced as untrusted data.
  • LLM only where it pays. generateExtractor() has the model write CSS selectors once. After that run() extracts with no LLM, and runOrHeal() regenerates the selectors when the site changes.
  • Local and free. No cloud, no API key, no per-page billing. You bring the proxy and, optionally, the model (OpenAI, Anthropic, Google, Ollama… through the Vercel AI SDK, or your own function).

Passes the bot detectors people actually use

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Browser Scraper: common questions

Is Browser Scraper MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the Browser Scraper safety report
How do I install Browser Scraper?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Browser Scraper need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Browser Scraper maintained?
The last commit was 6 days ago (2026-10-27). The latest release is v0.8.3.
What can I use instead of Browser Scraper?
Servers from other publishers that do the same job: Fortress MCP server, Oya Browser MCP server and WebReaper MCP server. Compare all Browser Scraper alternatives.
How does Browser Scraper compare with other Scraping and browsing MCP servers?
safety score 92/100 (higher than 85% of 868 Scraping and browsing servers); tools 13 (the typical Scraping and browsing server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Browser Scraper

Same job from other publishers: the closest match first, then the best rated.

All Browser Scraper alternatives →
  • Fortress
    Stealth browser for AI agents: fetch pages behind Cloudflare/DataDome/CAPTCHA, extract clean data.
    B
  • Oya Browser
    Real Chrome for agents: start a browser, read pages as numbered markdown, click, type, hand off.
    A
  • WebReaper
    AI-native web scraper: scrape, crawl and map any site to clean markdown over stdio. MIT-licensed.
    A
  • vibatchium
    Stealth browser automation for AI agents — real Chrome, N parallel persistent logged-in sessions.
    A
  • Zenpilot
    Let Claude use your Zen Browser, like Claude in Chrome. No extension, only sites you allow.
    A