scrape-technology avatar

Abrasio

scrape-technology/abrasio-mcp

Stealth browser for AI agents: navigate, click, type and extract on bot-protected sites.

GitHub stars
4
tools
17
auth
Secret needed
transport
STDIO
env vars
4
last updated
Nov 16, 2026

Tools

17 tools

Public tool metadata for what this MCP can expose to an agent.

browser_navigateNavigate to a URL and wait for the page to load.

Navigate to a URL and wait for the page to load.

No parameter schema in public metadata yet.

browser_go_backGo back to the previous page in browser history.

Go back to the previous page in browser history.

No parameter schema in public metadata yet.

browser_go_forwardGo forward to the next page in browser history.

Go forward to the next page in browser history.

No parameter schema in public metadata yet.

browser_reloadReload the current page.

Reload the current page.

No parameter schema in public metadata yet.

browser_get_urlGet the current page URL.

Get the current page URL.

No parameter schema in public metadata yet.

browser_screenshotTake a screenshot of the current page.

Take a screenshot of the current page.

No parameter schema in public metadata yet.

browser_get_textExtract all visible text from the current page body.

Extract all visible text from the current page body.

No parameter schema in public metadata yet.

browser_get_htmlGet the inner HTML of an element.

Get the inner HTML of an element.

No parameter schema in public metadata yet.

browser_find_elementsFind all interactive elements on the page.

Find all interactive elements on the page.

No parameter schema in public metadata yet.

browser_wait_forWait for an element to appear in the DOM.

Wait for an element to appear in the DOM.

No parameter schema in public metadata yet.

browser_clickClick an element by CSS selector.

Click an element by CSS selector.

No parameter schema in public metadata yet.

browser_fillClick a form input and fill it with text.

Click a form input and fill it with text.

No parameter schema in public metadata yet.

browser_typeType text at the current cursor position.

Type text at the current cursor position.

No parameter schema in public metadata yet.

browser_scrollScroll the page vertically.

Scroll the page vertically.

No parameter schema in public metadata yet.

browser_hoverMove the mouse over an element without clicking.

Move the mouse over an element without clicking.

No parameter schema in public metadata yet.

browser_pressPress a keyboard key or key combination.

Press a keyboard key or key combination.

No parameter schema in public metadata yet.

browser_evaluateExecute JavaScript in the current page context.

Execute JavaScript in the current page context.

No parameter schema in public metadata yet.

Sponsors

Configuration

ABRASIO_API_KEYsecret

Abrasio cloud API key (abr_live_...). Omit to run in free local mode. Get one at https://scrapetechnology.com/abrasio/register

ABRASIO_REGION

Target region for locale, timezone and cloud IP, e.g. BR or US

ABRASIO_HEADLESSdefault: true

Run the browser headless (true) or with a visible window (false)

ABRASIO_HUMANIZEdefault: false

Enable human-like interaction speed

Readme

abrasio-mcp

PyPI version License: MIT

MCP server that exposes Abrasio as an agentic browser for AI models.

Allows Claude, Cursor, and any MCP-compatible AI to control a real, managed stealth browser with realistic fingerprints — the same infrastructure used for web scraping, now driven by AI.

pip install abrasio-mcp   # or run without installing: uvx abrasio-mcp

Local mode is free and needs no API key. For cloud mode (managed browsers with real fingerprints and persistent profiles), get a key (abr_live_...) at scrapetechnology.com/abrasio/register. Docs: scrapetechnology.com/abrasio/docs.


How it works


View the full README on GitHub

Details

Repository
github.com/scrape-technology/abrasio-mcp
Website
scrapetechnology.com/abrasio
Categories
Web & Browser Automation, Search & Web Crawling
Package
abrasio-mcp
Transport
STDIO
Auth
Required
Registry
MCP registry, active

More from scrape-technology

Related Web & Browser Automation MCP servers

View all
1enreign avatarPagerunner — The Browser Layer That Learnsenreign/pagerunnerReal Chrome profiles with site intelligence — already logged in, PII anonymization, sessions persist3stars
2kc23go avatarAnybrowsekc23go/anybrowseConverts any URL to clean, LLM-ready Markdown using real Chrome browsers3stars
3carlosdmoron avatarScreen Mouse Recorder MCPcarlosdmoron/screen-mouse-recorder-mcpLocal MCP server that drives its own Chrome to record guided web tutorials.1stars
4dwytmcl avataranysitedwytmcl/anysite-mcpAny website as MCP tools: a real Chrome signed in as you, and shortcuts the agent saves as tools.1stars
5imrrd avatarPowershell Mcpimrrd/powershell-mcpHeadless Windows ops over MCP: hidden PowerShell plus in-process SSH, WinRM and SFTP.1stars
6fieldcure avatarAssiststudio Runnerfieldcure/fieldcure-assiststudio-runnerWindows-only headless LLM task automation engine with scheduling via Windows Task Scheduler.1stars