Browser Scraper MCP
A stealth browser automation and web scraping tool for Node.js that acts as an MCP server for AI agents. It uses a CDP-first approach with undetected Chrome to bypass bot protections like Cloudflare Turnstile and pierce closed Shadow DOM. It converts pages into clean Markdown, structured data, or accessibility snapshots, supporting features like Turnstile solving and coherent browser fingerprinting.
Package and access
Local package with source-attributed installation metadata. Koskamo does not execute packages during review.
What you can do with it
- Scrape web pages while bypassing anti-bot protections like Cloudflare Turnstile
- Extract clean Markdown and metadata from sites with closed Shadow DOM
- Provide an accessibility snapshot with clickable references for AI agents
- Automate browser interactions for Claude, Cursor, and Codex via MCP
Source and maintenance
- Maintenance checked
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
@eurafaeldecarvalho/browser-scraper 0.8.3
{
"version": "0.8.3",
"transport": "stdio",
"identifier": "@eurafaeldecarvalho/browser-scraper",
"registryType": "npm",
"packageArguments": [
{
"type": "positional",
"value": "mcp"
}
]
}Tools
Reported by the attributed source; not independently observed by Koskamo.
Connect from your client
Each snippet configures the same source-provided package; replace placeholders before use.
Cursor
{
"mcpServers": {
"browser-scraper-mcp": {
"command": "npx",
"args": [
"-y",
"@eurafaeldecarvalho/browser-scraper@0.8.3",
"mcp"
]
}
}
}Cline
{
"mcpServers": {
"browser-scraper-mcp": {
"command": "npx",
"args": [
"-y",
"@eurafaeldecarvalho/browser-scraper@0.8.3",
"mcp"
]
}
}
}VS Code
{
"servers": {
"browser-scraper-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@eurafaeldecarvalho/browser-scraper@0.8.3",
"mcp"
]
}
}
}Claude Desktop
{
"mcpServers": {
"browser-scraper-mcp": {
"command": "npx",
"args": [
"-y",
"@eurafaeldecarvalho/browser-scraper@0.8.3",
"mcp"
]
}
}
}Let your agent find its tools
Find servers like Browser Scraper MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.