Repository avatar
AI Tools
v0.1.1
active

abrasio-mcp

io.github.Scrape-Technology/abrasio-mcp

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

Documentation

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

AI Model (Claude, Cursor, etc.)
    │  MCP tool calls
    ▼
abrasio-mcp server
    │  Abrasio SDK
    ▼
Patchright (Playwright fork with stealth patches)
    │  CDP WebSocket
    ▼
Chrome (local stealth)  OR  Abrasio cloud worker (fingerprinted, residential IP)

The MCP server holds a single persistent browser session. The AI calls tools to navigate, observe, and interact — no configuration needed between steps.


Installation

pip install abrasio-mcp

Or install from source:

cd abrasio-mcp
pip install -e .

Modes

Local mode (free)

No API key required. Launches Chrome on your machine with Patchright stealth patches.

abrasio-mcp

Best for: development, testing, scraping sites that don't require real residential IPs.

Cloud mode (paid)

Requires an Abrasio API key. The browser runs on Abrasio cloud infrastructure with:

  • Real collected browser fingerprints (not spoofed)
  • Residential or datacenter IP in the target region
  • Persistent profiles that accumulate browser history
ABRASIO_API_KEY=abr_live_xxx abrasio-mcp

Best for: production agents, geo-targeted tasks, heavily protected sites.


Configuration

All configuration is done via environment variables. No config files required.

VariableDefaultDescription
ABRASIO_API_KEY(none)Cloud API key. If set, enables cloud mode. If unset, uses local mode.
ABRASIO_HEADLESStrueRun browser headless. Set false to see the browser window (local mode only).
ABRASIO_REGION(none)Target region for geo-configuration, e.g. BR, US, DE. Configures locale and timezone automatically.
ABRASIO_HUMANIZEfalseSet true to enable human-like interaction timing on all actions (slower but more realistic).
ABRASIO_TRANSPORTstdioMCP transport: stdio (default) or streamable-http (local-only, unauthenticated; see below).
ABRASIO_HOST127.0.0.1Bind host for streamable-http. Must be loopback (127.0.0.1, localhost or ::1); any other value makes the server refuse to start.
ABRASIO_PORT8931Bind port when using streamable-http transport.

Integrations

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "abrasio": {
      "command": "abrasio-mcp",
      "env": {
        "ABRASIO_API_KEY": "abr_live_xxx",
        "ABRASIO_REGION": "BR"
      }
    }
  }
}

For local mode (no API key):

{
  "mcpServers": {
    "abrasio": {
      "command": "abrasio-mcp",
      "env": {
        "ABRASIO_HEADLESS": "false"
      }
    }
  }
}

Claude Code

claude mcp add abrasio -- abrasio-mcp

With environment variables:

claude mcp add abrasio -e ABRASIO_API_KEY=abr_live_xxx -e ABRASIO_REGION=BR -- abrasio-mcp

Cursor

Add to .cursor/mcp.json in your project root:

{
  "mcpServers": {
    "abrasio": {
      "command": "abrasio-mcp",
      "env": {
        "ABRASIO_API_KEY": "abr_live_xxx"
      }
    }
  }
}

Streamable HTTP (local only)

The HTTP transport has no authentication by design, so it only binds to loopback (127.0.0.1, localhost or ::1). Anyone who could reach the port could drive the stealth browser and spend your credits; any other ABRASIO_HOST makes the server refuse to start.

Start the server:

ABRASIO_TRANSPORT=streamable-http \
ABRASIO_HOST=127.0.0.1 \
ABRASIO_PORT=8931 \
ABRASIO_API_KEY=abr_live_xxx \
abrasio-mcp

Configure the client to connect to http://127.0.0.1:8931/mcp.

For remote use, run the stdio transport over SSH, or keep the server on loopback and reach it through an SSH tunnel or an authenticated reverse proxy that you control.


Tools reference

The MCP server exposes 17 tools, organized in four groups.


Navigation

browser_navigate

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

ParameterTypeDescription
urlstringFull URL including scheme, e.g. https://example.com

Returns: JSON object with url (final URL after redirects), title, and status (HTTP status code).

{ "url": "https://example.com/home", "title": "Home — Example", "status": 200 }

browser_go_back

Go back to the previous page in browser history.

Returns: JSON object with url and title of the page navigated to.


browser_go_forward

Go forward to the next page in browser history.

Returns: JSON object with url and title.


browser_reload

Reload the current page.

Returns: JSON object with url and title.


browser_get_url

Get the current page URL.

Returns: String with the current URL.


Observation

browser_screenshot

Take a screenshot of the current page.

Returns: PNG image. Claude can see this image and use it to understand the visual state of the browser before deciding what to interact with.

Use this at the start of a task and after each major interaction to confirm the expected result.


browser_get_text

Extract all visible text from the current page body.

Returns: Plain text string. Useful for reading articles, prices, search results, or any text-based content without parsing HTML.


browser_get_html

Get the inner HTML of an element.

ParameterTypeDefaultDescription
selectorstringbodyCSS selector for the target element

Returns: HTML string of the matched element.


browser_find_elements

Find all interactive elements on the page.

Returns: JSON array. Each item represents a clickable, fillable, or otherwise interactive element:

[
  {
    "tag": "button",
    "type": "submit",
    "text": "Sign in",
    "href": null,
    "selector": "button.login-btn",
    "x": 720,
    "y": 412,
    "visible": true
  },
  {
    "tag": "input",
    "type": "email",
    "text": "",
    "href": null,
    "selector": "input[name=\"email\"]",
    "x": 720,
    "y": 340,
    "visible": true
  }
]
FieldDescription
tagHTML tag name
typeInput type (text, email, submit, etc.) or null
textVisible text, value, placeholder, or aria-label (up to 120 chars)
hrefLink URL for anchor elements
selectorCSS selector hint — use this with browser_click and browser_fill
x, yCenter coordinates in the viewport
visibleWhether the element is within the current viewport

Call browser_find_elements before interacting to get the correct selector for browser_click and browser_fill.


browser_wait_for

Wait for an element to appear in the DOM.

ParameterTypeDefaultDescription
selectorstring(required)CSS selector to wait for
timeoutinteger10000Maximum wait time in milliseconds

Returns: JSON object with found: true, the selector, and the element's text content.

Use this after triggering actions that cause loading states (form submissions, route changes, AJAX updates).


Interaction

All interaction tools use the Abrasio human simulation layer:

  • Clicks use WindMouse — a physics-based cursor movement algorithm that mimics real hand movement with gravity, wind perturbations, and velocity management.
  • Typing uses character-level timing with realistic delays, burst typing, and occasional typos followed by backspace correction.
  • Scrolling uses a 3-phase easing curve (acceleration → constant → deceleration).

browser_click

Click an element by CSS selector.

ParameterTypeDescription
selectorstringCSS selector for the element to click

Returns: Confirmation string.

Clicked: button#submit

browser_fill

Click a form input and fill it with text.

ParameterTypeDescription
selectorstringCSS selector for the input element
textstringValue to type into the field

Clears any existing value, clicks the field, then types with human-like timing.

Returns: Confirmation string with character count.

Prefer browser_fill over browser_type when targeting a specific input. Use browser_type only when the input is already focused.


browser_type

Type text at the current cursor position.

ParameterTypeDescription
textstringText to type

Types into whichever element currently has focus. Useful for keyboard shortcuts, search boxes that open on click, or multi-step typing flows.

Returns: Confirmation string with character count.


browser_scroll

Scroll the page vertically.

ParameterTypeDefaultDescription
pixelsinteger800Pixels to scroll. Positive = down, negative = up.

Returns: Confirmation string indicating direction and distance.


browser_hover

Move the mouse over an element without clicking.

ParameterTypeDescription
selectorstringCSS selector for the element to hover

Uses WindMouse movement to reach the element. Useful for revealing dropdown menus, tooltips, or hover-triggered UI elements.

Returns: Confirmation string.


browser_press

Press a keyboard key or key combination.

ParameterTypeDescription
keystringKey name or combination

Common values:

Key stringAction
EnterSubmit form / confirm
TabMove focus to next field
EscapeClose modal / cancel
ArrowDown / ArrowUpNavigate dropdowns
Control+aSelect all
Control+cCopy
Meta+ReturnSubmit (macOS)

Returns: Confirmation string.


Evaluation

browser_evaluate

Execute JavaScript in the current page context.

ParameterTypeDescription
scriptstringJavaScript expression or function

The script can be a simple expression or a function that returns a value:

// Expression
document.title

// Arrow function
() => document.querySelectorAll('h2').length

// Function with logic
() => {
  const el = document.querySelector('#price');
  return el ? el.innerText.trim() : null;
}

// Read localStorage
() => ({ token: localStorage.getItem('auth_token') })

Returns: JSON-serialized result of the script execution.

Use this for data extraction that browser_get_text and browser_get_html cannot handle — structured data, counts, computed values, or interacting with the page's JavaScript environment.


Patterns and best practices

Starting a task

Always begin with a screenshot to understand the current state:

1. browser_navigate("https://target.com")
2. browser_screenshot()           ← see what loaded
3. browser_find_elements()        ← discover available interactions

Filling a login form

1. browser_navigate("https://site.com/login")
2. browser_screenshot()
3. browser_find_elements()        ← get selectors for email/password fields
4. browser_fill("input[name='email']", "user@example.com")
5. browser_fill("input[name='password']", "secret")
6. browser_click("button[type='submit']")
7. browser_wait_for(".dashboard")  ← wait for redirect
8. browser_screenshot()            ← confirm login succeeded

Handling dynamic content

1. browser_click(".load-more-btn")
2. browser_wait_for(".new-items-loaded")   ← wait for content
3. browser_get_text()                      ← extract updated content

Extracting structured data

1. browser_navigate("https://shop.com/product/123")
2. browser_evaluate("() => ({ name: document.querySelector('h1').innerText, price: document.querySelector('.price').innerText })")

Navigating paginated results

1. browser_navigate("https://site.com/results?page=1")
2. browser_get_text()
3. browser_click("a[aria-label='Next page']")
4. browser_wait_for(".results")
5. browser_get_text()

Architecture

abrasio-mcp/
├── pyproject.toml
└── abrasio_mcp/
    ├── __init__.py
    ├── server.py          # FastMCP server, tool registration, entry point
    ├── browser.py         # AbrasioBrowserAgent — wraps Abrasio SDK + Page
    └── tools/
        ├── __init__.py
        ├── navigate.py    # browser_navigate, go_back, go_forward, reload, get_url
        ├── observe.py     # browser_screenshot, get_text, get_html, find_elements, wait_for
        ├── interact.py    # browser_click, fill, type, scroll, hover, press
        └── evaluate.py    # browser_evaluate

Session lifecycle

The browser session is lazy-started: the MCP server process starts immediately, and the browser only opens when the first tool is called. The session persists for the lifetime of the server process — navigation history, cookies, and localStorage are preserved across all tool calls.

On SIGTERM or SIGINT, the server calls Abrasio.close() which signals the worker to stop (in cloud mode) before dropping the CDP connection, ensuring proper billing finalization.

Browser agent (browser.py)

AbrasioBrowserAgent wraps Abrasio (the SDK's unified class) and holds a single Page object. All tools delegate to this agent. The asyncio.Lock on ensure_started prevents concurrent initialization if two tools are called in rapid succession before the browser is ready.

All interaction methods use the human/actions.py primitives from the Abrasio SDK directly — no custom mouse or keyboard simulation is implemented in abrasio-mcp.


Requirements

  • Python 3.10+
  • mcp >= 1.8, < 2 (the server uses the v1 FastMCP API)
  • abrasio >= 0.1.2 (installs patchright automatically)
  • For cloud mode: an Abrasio API key (abr_live_...) — get one at scrapetechnology.com/abrasio/register

License

MIT — Scrape Technology

PYPI
abrasio-mcp
Install Command
pip install abrasio-mcp
Runtime: uvx