PluginBench
MCP Server
Active
MIT

invisible_playwright_mcp MCP Server

io.github.feder-cr/invisible-playwright-mcp

AI browser agent that automates web browsing from plain-English instructions while evading anti-bot detection.

What is the invisible_playwright_mcp MCP server?

The invisible_playwright_mcp MCP server is an AI browser agent that automates real web browsing—clicking, typing, reading—from natural-language instructions. It uses a stealth-configured browser to avoid captchas and anti-bot systems, and integrates with Claude, Cursor, and other AI assistants via MCP or runs standalone with a web UI.

This server lets AI agents interact with real websites the way a human would, handling dynamic content, calendar widgets, and complex navigation that APIs cannot. It's useful for price comparison, form filling, data extraction, and any task requiring human judgment about what's displayed on a live web page. The browser runs locally on your machine with optional proxy support and anti-detection measures.

How to install invisible_playwright_mcp

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "invisible-playwright-mcp": {
      "command": "uvx",
      "args": [
        "invisible-playwright-mcp"
      ]
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

  • browse — Navigate to a URL and read the page content
  • click — Click elements on the page by coordinates or selectors
  • type — Type text into form fields and input elements
  • read — Extract and read text and data from the current page
  • screenshot — Capture a screenshot of the current browser state

Use cases

  • Compare flight prices across multiple dates by clicking calendar widgets and reading fares
  • Fill out complex web forms with multi-step navigation and dynamic content
  • Extract data from websites that require interaction (login, pagination, filtering)
  • Automate travel booking and e-commerce tasks that require human judgment about page content
  • Monitor and interact with JavaScript-heavy single-page applications

invisible_playwright_mcp MCP server FAQ

What is the invisible_playwright_mcp server?

It's an AI browser agent that automates web browsing from plain-English instructions. Unlike other browser agents, it uses anti-detection techniques to avoid captchas and anti-bot systems.

Is it free to use?

The server itself is free and open-source (MIT license). Using it requires an OpenRouter API key (paid) or integration with your own AI assistant via MCP.

How do I install it in Claude or Cursor?

Install via the plugin marketplace: `claude plugin marketplace add feder-cr/invisible_playwright_mcp` then `claude plugin install invisible-playwright-mcp@feder-cr`. For Cursor and other assistants, use the MCP server configuration with the PyPI package `invisible-playwright-mcp`.

Do I need authentication?

You need an OpenRouter API key if using the standalone web UI. When integrated via MCP, your AI assistant handles authentication with its own model provider.

Does it require a proxy?

No, proxy is optional. You can set one with `--proxy` to change timezone, locale, and IP egress for anti-detection purposes.

What data does it collect?

None. The server runs entirely on your machine. Only the websites you visit, your model provider, and GitHub (for engine downloads and GeoIP data) see any traffic.

README (reference)

Source of truth, from the repository.

<div align="center"> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/feder-cr/invisible_playwright_mcp/main/assets/masks-dark.png"> <img alt="invisible_playwright_mcp" src="https://raw.githubusercontent.com/feder-cr/invisible_playwright_mcp/main/assets/masks-light.png" width="150"> </picture>

Other AI browser agents get captchas. This one is invisible to anti-bots.

</div>

Two ways to use this browser agent

1. From your assistant, over MCP

Windows, in PowerShell:

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
$env:Path = "$env:USERPROFILE\.local\bin;$env:Path"

Linux:

curl -LsSf https://astral.sh/uv/install.sh | sh
source $HOME/.local/bin/env

Then install it in your assistant.

Claude Code:

claude plugin marketplace add feder-cr/invisible_playwright_mcp
claude plugin install invisible-playwright-mcp@feder-cr

Codex:

codex plugin marketplace add feder-cr/invisible_playwright_mcp
codex plugin add invisible-playwright-mcp@feder-cr

Gemini CLI:

gemini extensions install https://github.com/feder-cr/invisible_playwright_mcp

2. Standalone: the web UI

We bring the interface, you bring an OpenRouter key. Chat on the left, the live browser on the right.

Windows, in PowerShell:

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
$env:Path = "$env:USERPROFILE\.local\bin;$env:Path"
uvx invisible-playwright-mcp ui --openrouter-key sk-or-...

Linux:

curl -LsSf https://astral.sh/uv/install.sh | sh
source $HOME/.local/bin/env
uvx invisible-playwright-mcp ui --openrouter-key sk-or-...

Then open http://127.0.0.1:8765 and type the same thing.


What to ask a web browsing agent

Anything that needs real web automation: a browser rather than an API, and a person's judgement about what is on the page.

Go to <paste the URL>. One way, Milan to Lisbon, economy, one checked bag, one adult. Check every date from the 12th to the 16th of next month, one at a time, and read the cheapest fare for each day. The date field is a calendar widget, so click the days rather than typing them. If a date has no availability, say so. Do not guess a number.

It drives the page the way a person would: the pointer moves, keys are pressed.

Options: proxy, profile, seed

  • --openrouter-key Your key, or the OPENROUTER_API_KEY variable.
  • --model An OpenRouter model id, or INVISIBLE_MCP_MODEL. Defaults to z-ai/glm-5.3-flash.
  • --proxy Optional. http://user:pass@proxy.example.com:8080 or socks5://proxy.example.com:1080. Host and port are both required. The timezone, locale and egress follow it.
  • --binary An engine binary you already have. It must be the build the seal pins, or startup refuses: this skips the download, not the version check.
  • --seed An integer. Same seed, same browser identity, every run.
  • --profile-dir A directory to keep the profile in, so logins and cookies survive restarts.
  • --headed Show the browser window. The interface shows you the page anyway.
  • --host, --port 127.0.0.1 and 8765. Changing the host exposes an interface that has no authentication.

A .env beside the command

Rather than retyping the key and the binary path, put them in a .env in the directory you run from:

OPENROUTER_API_KEY=sk-or-...
STEALTHFOX_BINARY=/path/to/firefox

It is read at startup, and on the way in it never overrides something already set, so the order is --flag > the environment > .env > the default. Only the directory you are in is read - there is no search upwards, so running from a subfolder cannot silently pick up a different key. The startup line names the variables it applied and never prints their values.

Passing --openrouter-key puts the key in your shell history, and on Linux in the process list. OPENROUTER_API_KEY in the environment or in a .env avoids both.

The wiki: AI browser-agent guides

The reading room around the agent lives in the wiki: the AI browser-agent landscape: browser-use, Operator-style and computer-use agents compared, what to check when an agent gets blocked, and what happened to OpenAI Operator, among others. Worked examples, transcripts and their outputs live in articles/.

The rest of the family: engine, core

The MCP server from option 1 ships inside this package: invisible_playwright_mcp with no subcommand is the server, invisible-playwright-mcp ui the interface. Its config blocks for clients that take a file, its settings and its tools are on the wiki page The MCP server.

  • invisible_playwright The engine, as a Python library, for writing code instead of prompts. The API is Playwright's.
  • invisible_core Seed to fingerprint to preferences, proxy and geolocation.

Using it responsibly

This automates a browser under your control. Read the terms of the sites you point it at, respect their rate limits, and do not submit anything a human has not read.

Privacy Policy

This browser agent runs on your machine and has no server of its own. What leaves your computer, and to whom:

  • The sites you visit see the browser, as they would any Firefox.
  • Your model provider. The web UI sends the conversation and what the agent reads on the page to OpenRouter under your key. Over MCP, the client you plugged it into does the same with whichever model it uses.
  • GitHub. The engine is downloaded from a GitHub release the first time the server or the interface starts, and a GeoIP database is when a proxy is set. Each browser launch also fetches a one-line counter file from a GitHub release, which is how launches are counted: the request carries no identifier and nothing of yours, and GitHub sees what any HTTPS request shows, your IP address.

Nothing else is collected and nothing is sent to the author. Sessions, profiles and screenshots are stored locally, under INVISIBLE_MCP_HOME if set and otherwise in the application-data directory of your system, and are yours to delete; nothing is retained anywhere else. Questions go to the issues.

License

MIT. Everything distributed before 2 September 2026 was released under AGPL-3.0 and stays under it.

<!-- The Official MCP Registry verifies ownership of a PyPI package by finding this token in the published description, which is this file. It must match the `name` in server.json exactly. --> <!-- mcp-name: io.github.feder-cr/invisible-playwright-mcp -->

Related MCP servers

AIAIHawk logo

AIHawk

Active

AI browser agent that automates web tasks invisibly—clicks, types, reads real pages from plain-English instructions.

32k
Python
MIT
View repository →

Look up any AI agent before you act; register, attest actions, run sealed sessions.

View repository →
AGAgent Rails logo

Shopping MCP for AI agents: search, compare, Amazon buy links. Auto-register.

0
C#
View repository →

Autonomous research engine: auto research from a prompt to a fully-cited academic paper via MCP

1
Python
View repository →

Create AI surveys with dynamic follow-up probing directly from your AI assistant.

2
Python
MIT
View repository →

Real-time macroeconomic signals for AI agents. 86 FRED series, regime classification, DeFi rates.

1
View repository →