mcpField
N
nokk

nokk

Local
github.comBrowser Automation21Updated today

About nokk

nokk is a Rust headless browser engine for AI agents and browser automation users. It provides a Chrome-like fingerprint and CDP access without a rendering engine, and can run as an MCP server.

Key features

  1. 01Chrome-like TLS and JavaScript fingerprint
  2. 02CDP navigation and page scripting
  3. 03Cloudflare challenge solving
  4. 04Persistent named sessions
  5. 05Rotating browser-context fingerprints
  6. 06CLI, Python, and Node interfaces

Use cases

  1. 01Loading pages gated by Cloudflare
  2. 02Driving pages through Puppeteer or Playwright
  3. 03Extracting page text and DOM data
  4. 04Giving AI agents browser tools through MCP

MCP support

Run `nokk-mcp` as an MCP server for AI agents. It exposes tools to open and inspect pages, interact with elements, evaluate scripts, and handle challenges.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"koloss777-nokk": {
"command": "uvx",
"args": [
"nokk-mcp"
],
"env": {
"NOKK_PROXY": "<NOKK_PROXY>",
"NOKK_ROTATE_FINGERPRINT": "<NOKK_ROTATE_FINGERPRINT>",
"NOKK_NO_AUTO_SOLVE": "<NOKK_NO_AUTO_SOLVE>"
}
}
}
}
Run commanduvx nokk-mcp
Environment variables to set
NOKK_PROXYUpstream proxy, e.g. socks5://host:1080
NOKK_ROTATE_FINGERPRINT1: each session gets its own coherent fingerprint
NOKK_NO_AUTO_SOLVE1: do not solve challenges during navigation

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypinokk-mcp0.1.46a1

Tools

10

Saved tool list · updated 3d ago

ParameterTypeRequiredDescription
urlstringYes

Details

From the project README
nokk

A stealth headless browser engine in Rust. Passes Cloudflare without Chromium.

Real V8 and a DOM, a Chrome TLS/HTTP fingerprint (JA3/JA4) and JS-level stealth, driven over the Chrome DevTools Protocol: Puppeteer and Playwright connect as usual. Also an MCP server for AI agents.

CI Release PyPI npm Docker Rust License: MIT OR Apache-2.0 Status: alpha

curl gets 403 from a Cloudflare test page; nokk loads it, clears the challenge and prints the page behind it in about 5 seconds

scrapingcourse.com's Cloudflare test page, one run from a home connection; medians across sites are in the tables below.

The nøkk is a shapeshifting water-spirit of Norse myth that takes on a familiar shape to pass unnoticed. This one takes the shape of Chrome.


Install

pip install nokk                    # Python: the prebuilt binary is in the wheel
npm install @koloss777/nokk         # Node: run it with `npx nokk`
docker run --rm -p 9222:9222 ghcr.io/koloss777/nokk:latest

No browser to download. Prebuilt for Linux (x86_64, ARM64), macOS on Apple Silicon and Windows x64; anything else builds from source.

Quick start

# Load a page behind Cloudflare, clear the challenge, print what is behind it
nokk --load https://www.scrapingcourse.com/cloudflare-challenge --solve-challenge 30 \
     --eval "document.querySelector('h2').textContent.trim()"

# Or run the CDP server and drive it from any client
nokk --port 9222 --auto-solve   # ws://127.0.0.1:9222/devtools/browser/nokk
import nokk
from playwright.sync_api import sync_playwright

with nokk.launch(auto_solve=True) as server, sync_playwright() as pw:
    page = pw.chromium.connect_over_cdp(server.ws_endpoint).new_page()
    page.goto("https://www.scrapingcourse.com/cloudflare-challenge")
    print(page.title())

For AI agents, uvx nokk-mcp runs it as an MCP server. Puppeteer, Node, sessions and the Cloudflare options are below.

Why nokk

Puppeteer and Playwright drive a real Chromium, and anti-bot systems spot it through navigator.webdriver, CDP artifacts and a headless TLS handshake. nokk is built to look like Chrome from the TLS handshake to the JavaScript environment, and has no rendering engine at all.

nokk 0.1.35Chrome 151 (Puppeteer / Playwright)
Start until CDP answers~0.05 s~0.2 s
Idle memory (PSS)~60 MB, 1 process~330 MB, 12–14 processes
Cloudflare solve, median wall time12.4 s12.4 s
Slowest solve15.6 s27.8 s
CPU per solve6.4 s9.5 s
Peak memory per solve~570 MB~720 MB
Solved24/2424/24
TLS fingerprint (JA3/JA4)matches Chrome 151Chrome
Screenshots, PDF, layoutnoyes
CDP coveragethe common pathfull

Measured on nokk 0.1.35, an 8-core Linux box, October 2026. Cloudflare row: 8 production sites × 3 runs through one proxy, nokk with --until-clearance, Chrome driven by a checkbox-clicking harness; a solve counts only if the site then opens with the cookie.

Not for you if you need screenshots, PDFs, layout or paint, or the whole Playwright/CDP surface: nokk has no rendering engine by design, and its CDP coverage is the path Puppeteer and Playwright use for navigation and scripting.

Measured on public pages

Three runs per page from the CLI with --solve-challenge 30 and no proxy, on an 8-core Linux box (October 2026). The time is the whole command, from process start to the printed result. Run them yourself with tools/cf-check.sh.

PageChallengeSolvedMedianSlowest
chess.com/logininvisible Turnstile widget on a live site3/37 s9 s
scrapingcourse.com/cloudflare-challengemanaged interstitial3/35 s7 s
peet.ws/turnstile-test/managed.htmlmanaged widget3/37 s8 s
peet.ws/turnstile-test/non-interactive.htmlnon-interactive widget3/33 s4 s
nopecha.com/demo/cloudflareinteractive interstitial with a checkbox3/310 s11 s

On production sites behind Cloudflare the result is in the comparison above: 8 sites, 24 of 24 solved. Those sites are not named here.

Usage

Command line
nokk --fetch https://tls.browserleaks.com/json                   # Chrome TLS + HTTP/2 fingerprint
nokk --load https://example.com --eval 'document.title'          # run the page, query the DOM
nokk --load https://quotes.toscrape.com --dump-requests          # every request the page makes
nokk --load https://target --proxy socks5://host:1080            # through a proxy
nokk --port 9222 --rotate-fingerprint --geoip-timezone           # CDP server, a machine per context

Ad, analytics and tracker requests are dropped by default; --allow-trackers loads them. Anti-bot vendors are never blocked, because they must run to hand out a token.

Puppeteer
import puppeteer from 'puppeteer';

const browser = await puppeteer.connect({
  browserWSEndpoint: 'ws://127.0.0.1:9222/devtools/browser/nokk',   // nokk --port 9222
});
const page = await browser.newPage();
await page.goto('https://example.com');
console.log(await page.title());
Node and Python

Both packages carry the prebuilt binary and start the CDP server for you.

const server = await require("@koloss777/nokk").launch({ autoSolve: true });
// server.wsEndpoint -> puppeteer.connect / chromium.connectOverCDP
with nokk.launch(auto_solve=True) as server:   # or: await nokk.launch_async()
    ...  # server.ws_endpoint -> connect_over_cdp
crawl4ai, Scrapy, Playwright MCP and other CDP tools

Anything that drives Chrome over CDP can drive nokk instead. crawl4ai, stopped by Cloudflare with its own Chromium, gets the page behind it through nokk: BrowserConfig(browser_mode="custom", cdp_url=server.ws_endpoint). Scrapy (scrapy-playwright's PLAYWRIGHT_CDP_URL) and Playwright MCP (--cdp-endpoint) work the same way. See docs/integrations.md.

For AI agents (MCP)

nokk runs as a Model Context Protocol server, so an agent such as Claude Desktop or Claude Code browses through the fingerprinted engine. With uv nothing needs installing first:

{ "mcpServers": { "nokk": { "command": "uvx", "args": ["nokk-mcp", "--rotate-fingerprint"] } } }

Without uv: pip install "nokk[mcp]", then "command": "python", "args": ["-m", "nokk.mcp"]. Tools: open, read_text, read_html, click, fill, evaluate, links, solve_challenge, challenge_state, reset.

Cloudflare challenges

nokk clears Turnstile by itself: the invisible widget, the managed interstitial and the interactive Verify you are human checkbox. Nothing is configured per site. Where a widget needs a press, the engine presses it like a person would.

  • --solve-challenge N sets the time budget, and --fail-on-challenge exits 3 if a gate is still up.
  • --until-clearance stops at a fresh cf_clearance and skips the heavy page behind the gate.
  • --auto-solve does the same for every page.goto() over CDP; Nokk.solveChallenge does it on demand.
  • A cf_clearance from a real browser can be imported, because nokk's JA4 matches Chrome 151.

Details, the CDP methods and events: docs/cloudflare.md.

Persistent sessions

--session-store ./sessions saves each named session's cookie jar, cf_clearance included, to disk and reloads it in a new process. Warm a session once and reuse it instead of solving the challenge on every run. See docs/sessions.md.

Rotating fingerprints

--rotate-fingerprint gives every browser context its own coherent machine: TLS emulation, User-Agent, client hints, platform, screen and WebGL all agree. --geoip-timezone matches the timezone and languages to the proxy's exit IP. See docs/fingerprints.md.

Builds

BuildWhat it addsWhere
light (default)everything above; canvas and WebGL pixels are synthesisedpip, npm, ghcr.io/koloss777/nokk:latest, nokk-*.tar.gz
renderreal canvas 2D and WebGL rasterisation, about 100 MB more at peak:render image, nokk-render-*.tar.gz, --features render,webgl

Prebuilt for Linux x86_64 and ARM64, macOS on Apple Silicon and Windows x64; the render build for Linux x86_64. Docker variants, the archives and building from source are in docs/install.md.

How it works

A Cargo workspace of small crates: a V8 isolate pool, a Chrome-fingerprinted HTTP client on BoringSSL, an html5ever DOM, the stealth layer and a CDP server. Concurrency is one isolate per thread with many contexts each, all IO runs on tokio off the isolate threads, and the JS fingerprint and the TLS fingerprint always agree. More in docs/architecture.md.

Project status

Alpha. The engine is real and end-to-end: V8 executes page JS against a parsed DOM, the fingerprinted transport clears Cloudflare's TLS/HTTP checks, the engine solves Turnstile on live sites — invisible, managed and interactive — and Puppeteer and Playwright connect over CDP to open a page, navigate, and evaluate.

What is not done yet, and where the sharp edges are:

  • JS-fingerprint hardening is ongoing. Much of the hardening is in place — native toString masking, internals hidden from Object.getOwnPropertyNames, navigator/screen as real prototype instances, an IP-coherent timezone, and per-context coherent fingerprint rotation, Web Workers, canvas/WebGL/WebGPU/audio with Chrome's pixels and samples, Trusted Types and CSP. nokk solves Cloudflare's challenges today, and the comparison against Chrome section by section is how the remaining tells get found; it is not yet a match for a dedicated fingerprinting suite like CreepJS. See the roadmap.
  • CDP coverage is the common path, not the whole protocol. Puppeteer and Playwright connect over CDP: navigation, evaluate, $ / $eval / $$eval, title(), url(), new pages and CDP sessions are tested; less-common domains are not implemented yet.
  • Per-context cookie isolation and per-session persistence work (each browser context gets its own jar; named sessions persist across runs); per-host / per-proxy / global connection limits are not yet enforced (Phase 7).
  • No rendering — screenshots, PDF, and layout/paint are out of scope by design.

See ROADMAP.md for the phased plan and the concrete hardening backlog.

Contributing

Issues and PRs are welcome — the hardening backlog in the roadmap is a good place to start. Before sending a change:

cargo fmt
cargo clippy --all-targets
cargo test

License

Licensed under either of MIT or Apache-2.0 at your option.

Unless you explicitly state otherwise, any contribution you submit for inclusion in this work, as defined in the Apache-2.0 license, shall be dual-licensed as above, without any additional terms or conditions.


nokk is an independent research project and is not affiliated with Google, Chrome, or any anti-bot vendor. Use it only against systems you are authorized to test.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.