Eyebrowse

Why EyeBrowse?

• 🥷 Stealth by default — engine-level fingerprint spoofing (geoip + humanize on out of the box, novel fingerprint per launch); navigator.webdriver masked; viewport auto-sized to the spoofed screen. No puppeteer-extra band-aids — the anti-detection is compiled into the browser.
• 🤖 Built for LLMs — pages are read as an ARIA tree with [ref=…] handles; the model acts by ref (click/type/hover), not by brittle CSS or raw pixels. Cross-origin iframes, shadow DOM, popups — handled.
• ⚡ Chrome DevTools Protocol — trusted, cursorless clicks by node ref (Input.dispatchMouseEvent), raw Network/Performance/Emulation access, MHTML snapshots, PDF export, and native video — all reachable as tools.
• 🧰 Library and MCP from one codebase — a clean Python API (EyeBrowse + Session), mirrored 1:1 by a thin MCP server (85 browser_* tools) for Claude Code and any MCP client.
• 🪟 Never boxed in — the curated high-level API doesn't hide Playwright: reach session.page / .context / .browser for anything it doesn't wrap.
• 🔋 Batteries included — multi-session, proxy + identity rotation, API-mode captcha solvers, native video, full HAR capture, and clean-markdown extraction.

Scope. EyeBrowse is a low-level browser engine — it holds no workflow logic. Consumers decide what to do; the engine provides what's possible.

Contents

Quickstart · Install · Features · Compare · Library · MCP · Proxy & identity · Extraction · Recording · How it works · Caveats · Tools · License

Quickstart

pip install eyebrowse# The stealth-Chromium binary downloads automatically on first launch — nothing else to run.

import asynciofrom eyebrowse import EyeBrowse
async def main():    eb = EyeBrowse()                          # stealth defaults: geoip · humanize    async with eb.session() as s:        await s.navigate("https://example.com")        print(await s.snapshot())             # ARIA tree with [ref=...] handles        await s.click("e6")                   # act on a ref from the snapshot    await eb.aclose()
asyncio.run(main())

…or wire it into Claude Code (or any MCP client) — see Use over MCP.

Install

From PyPI

pip install eyebrowse                 # or: uv pip install eyebrowse# CloakBrowser fetches its Chromium binary lazily on first launch — nothing to run.pip install "eyebrowse[extract]"     # optional: + Crawl4AI markdown extraction (heavier)

From source (development)

git clone https://github.com/Evil-Bane/eyebrowse && cd eyebrowseuv sync                              # core engine  (add --extra extract for Crawl4AI)cp .env.example .env                 # only if you use a proxy / captcha keys

Python 3.12 (pinned <3.13). Engine: cloakbrowser>=0.3 (stealth Chromium, Chrome/146), on playwright 1.60 and mcp 1.27.

Features

Full per-tool reference: docs/TOOLS.md (85 tools across 18 groups).

How EyeBrowse compares

_{Fair-use note: each project targets a different niche — this compares them on the axes EyeBrowse optimizes for (stealth + LLM-drivable + one library/MCP codebase), not as an overall ranking.}

Use as a library

import asynciofrom eyebrowse import EyeBrowse
async def main():    eb = EyeBrowse()                           # stealth defaults    try:        async with eb.session() as s:          # a stealth session (auto-closed)            await s.navigate("https://example.com")            print(await s.snapshot())          # ARIA tree with [ref=...] handles            await s.click("e6")                # act on a ref            await s.type("e8", "hello", submit=True)            png = await s.screenshot(full_page=True)            title = await s.page.title()        # full Playwright power when you need it    finally:        await eb.aclose()
asyncio.run(main())

Run the included proof: uv run python examples/direct_usage.py.

Use over MCP

EyeBrowse ships an MCP server (eyebrowse-mcp, FastMCP over stdio). Add it to any MCP client.

Claude Code (CLI):

claude mcp add eyebrowse -- eyebrowse-mcp

Any MCP client (JSON config):

{  "mcpServers": {    "eyebrowse": {      "command": "eyebrowse-mcp"    }  }}

Then drive the loop: browser_navigate(url) → read the snapshot → act by ref (browser_click / browser_type / …). A default session is auto-created, so most tools just work. Full list: docs/TOOLS.md.

Proxy & identity (optional)

Runs proxyless by default (geoip still aligns locale/timezone to your real IP). Add a proxy only when you want one:

await eb.new_session(proxy="http://user:[email protected]:8080")await eb.rotate_identity(proxy="socks5://host:1080")   # fresh fingerprint + paired IPawait eb.new_session(no_proxy=True)                     # force proxyless

Set a default once via EYEBROWSE_PROXY_* in .env, eb.set_static_proxy(...), or a custom ProxyProvider for rotation. Over MCP: browser_new_session(proxy_url=…) / browser_new_identity(proxy_url=…) / browser_set_proxy(…).

reCAPTCHA v3 / reputation gates are score-based and key off IP + session reputation — a fresh browser on a flagged IP fails regardless of stealth. Pair EyeBrowse with a clean residential proxy.

Extraction

eb.extract() (or browser_extract) hands the rendered HTML to Crawl4AI's raw: feed and returns clean, pruned markdown — no LLM is called and no LLM keys are ever read; the consuming agent does any structuring.

md  = await eb.extract()                            # markdown stringres = await eb.extract(output_path="data/page.md")  # → {"path": ..., "chars": ...}

Recording

Native video — Playwright records the whole session to a .webm, written on close. The path is known up-front; the file finalizes when the session closes:

s = await eb.new_session(record_video=True)# ... drive the browser ...print(await s.video_path())          # path is known up-front; file finalizes on closeawait eb.close_session(s.id)

Over MCP: browser_new_session(record_video=True) → browser_video_path. Want a GIF for a README? Convert the .webm with ffmpeg (ffmpeg -i demo.webm demo.gif). The demo at the top was captured this way — see examples/make_demo.py.

How it works

CONSUMERS                         ENGINE (library: eyebrowse/) Claude Code  ──MCP──▶  mcp/  ──▶  EyeBrowse façade (public API) your code   ─ import ──────────▶   ├─ BrowserEngine (CloakBrowser / stealth Chromium) any MCP client                     ├─ proxy / identity rotation (pluggable)                                    ├─ captcha solvers (pluggable, API-mode)                                    └─ Crawl4AI (raw: feed) → clean markdown

The façade (EyeBrowse + Session) is the product; the MCP adapter is a thin 1:1 wrapper over it. The high-level API is curated and LLM-friendly — not a reimplementation of all of Playwright — and the raw page / context / browser objects are always one attribute away. The launcher is the only engine-specific layer; everything else is plain Playwright.

Caveats

Worth knowing:

• evaluate runs in the page's main world (page globals reachable). To override a page's widget globals and fire a site callback (e.g. for captcha), EyeBrowse injects a <script> so the code runs in the page world — see captcha/inject.py.
• HAR export closes the session — Playwright only flushes the HAR buffer when the context closes. Use the checkpoint pattern: browser_storage_state → browser_har_export → browser_new_session(storage_state=...). For the initiator-rich Chrome HAR (JS call stacks), reach the Network.* domain via browser_cdp_send.
• Native video is .webm — convert to GIF/MP4 with ffmpeg if you need another format.

Project layout

eyebrowse/  api.py            EyeBrowse façade — the single public entry point  config.py         settings / secrets (pydantic-settings)  snapshot.py       aria_snapshot(mode="ai") + aria-ref= resolution  proxy.py          ProxyConfig + pluggable ProxyProvider  identity.py       Identity + random_identity() (isolated profile dir)  extract.py        Crawl4AI raw: feed → markdown (lazy, optional dep)  engine/           engine.py (CloakBrowser launch) + session.py (verbs + registry)  captcha/          solver ABC + 4 providers + DOM detect/inject  mcp/              FastMCP server + state + tools/ (18 groups · 85 tools)examples/direct_usage.py   library proof (no MCP)examples/make_demo.py      the native-video demo abovedocs/TOOLS.md              full tool reference

Build notes, version-pin rationale, and verified engine behavior live in CLAUDE.md.

Use responsibly

EyeBrowse drives a real browser with anti-detection features. Use it only against sites you own or are explicitly authorized to automate, and within their terms and applicable law.

License

MIT © Evil-Bane