Browser Scraper MCP Server

by eurafaeldecarvalho Your server? Claim it

local only

Browser Scraper runs on your own machine — the client starts it, so there is no endpoint to ping. 504 installs a week from npm. Last commit 27 Oct 2026.

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

Installs per day peak 353 · avg 31 · +38% w/w

a month agotoday

504

Installs / week

npm · @eurafaeldecarvalho/browser-scraper

Stars

0 open issues

27 Oct 2026

Last commit

4 releases in 90 days

MIT

License

TypeScript

What the code does

We read the source, 5 d ago · rules 995398eba69f

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Runs an external command src/core/http.ts:274, src/core/browser.ts:474

    child = spawn(bin, args, { stdio: ["ignore", "pipe", "pipe"] });

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add browser-scraper -- npx -y @eurafaeldecarvalho/browser-scraper

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "browser-scraper": {
      "command": "npx",
      "args": [
        "-y",
        "@eurafaeldecarvalho/browser-scraper"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.browser-scraper]
command = "npx"
args = ["-y", "@eurafaeldecarvalho/browser-scraper"]

.cursor/mcp.json

{
  "mcpServers": {
    "browser-scraper": {
      "command": "npx",
      "args": [
        "-y",
        "@eurafaeldecarvalho/browser-scraper"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "browser-scraper": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@eurafaeldecarvalho/browser-scraper"
      ]
    }
  }
}

Alternatives to Browser Scraper

same job, measured the same way

Fortress

by tiliondev

Stealth browser for AI agents: fetch pages behind Cloudflare/DataDome/CAPTCHA, extract clean data.

469 installs/wk local only

Oya Browser

by oyadotai

Real Chrome for agents: start a browser, read pages as numbered markdown, click, type, hand off.

answering

Wick

by wickproject

Browser-grade web access for AI agents. Fetches any webpage, returns clean markdown.

76 installs/wk local only

Wick

by myleshorton

Browser-grade web access for AI agents. Fetches any webpage, returns clean markdown.

local only

Neo Vision

by matthewalexong

Spatial DOM maps for AI agent browser navigation with anti-bot stealth.

65 installs/wk local only

screenshot.com.ar

by com-screenshot

Screenshots and clean markdown of any public web page, rendered in a real Chrome browser.

answering

Unblink

by christopherdavenport

Pure-Go browser for AI: fetch pages, render JS without Chromium, return clean Markdown over MCP.

local only

Web Tools for AI Agents

by projectworks007

Web tools for AI agents: URL to clean Markdown, site crawl, screenshots, PDF/Office to text, OCR.

answering

Browser Scraper — questions

Answers built from our own checks of this server.

Why is there no uptime for Browser Scraper?

Browser Scraper runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package @eurafaeldecarvalho/browser-scraper was installed 504 times last week.

How do I connect Browser Scraper?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls @eurafaeldecarvalho/browser-scraper straight from npm; nothing to host, nothing to sign up for.

How many people use Browser Scraper?

The npm package @eurafaeldecarvalho/browser-scraper was installed 504 times in the last week. Week over week that is +38%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Browser Scraper open source?

Yes — it is published under the MIT licence, written in TypeScript and 11 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.