A browser MCP server with a real identity
Add Clearcote to your MCP client's config and the model gets a browser it can read, click and type in through about twenty tools. The identity is set once, in environment variables, so the tool list stays short and the fingerprint stays consistent while the agent works.
Runs the open build with no key. Add a free GitHub key for the latest build.
Add it to your client's config
{
"mcpServers": {
"clearcote": {
"command": "npx",
"args": ["-y", "clearcote-mcp"],
"env": {
"CLEARCOTE_FINGERPRINT": "acct-1",
"CLEARCOTE_TIMEZONE": "America/New_York",
"CLEARCOTE_ACCEPT_LANGUAGE": "en-US"
}
}
}
}Highlights
About twenty tools
read_page, page_elements, click, fill_field, screenshot and navigate, plus scrolling, waiting, tabs, cookies, localStorage and profiles.
Identity outside the prompt
Seed, platform, brand, language and timezone are CLEARCOTE_* environment variables. The model never has to reason about fingerprints.
The clients you already use
Claude Desktop, Cursor and Cline share the same config shape. Run it from npm with npx, or install it from PyPI.
No automation switch
The server drives the browser over CDP, so navigator.webdriver stays false, and the engine neutralises the Runtime.enable side effect that usually reveals an attached client.
A way out to raw CDP
get_cdp_endpoint returns the browser's CDP URL, so a script can pick up the same session the agent was working in.
The latest build, one variable
Add CLEARCOTE_LICENSE_KEY to run the latest licensed build instead of the open one.
How the MCP server works
The server starts one Clearcote browser and keeps it for the conversation. Each tool call acts on that shared browser: the model reads the page as text or markdown, lists the interactive elements with stable references, and acts on them by reference, which holds up better than asking a model to write selectors.
The identity is fixed when the server starts. Everything the fingerprint flags control is available as a CLEARCOTE_* variable, so one server entry is one identity, and no tool can change it halfway through a task.
There are two ways to put a model in charge of Clearcote. This server keeps the model outside the browser, calling tools. The in-browser agent runs inside the browser process instead, and talks to an OpenAI-compatible endpoint you choose.
The most-used tools
| Tool | What it does |
|---|---|
read_page | Read the live page as text or markdown |
page_elements | List interactive elements with stable references |
click | Click an element |
fill_field | Type into an input or textarea |
screenshot | Capture the viewport or the full page |
navigate | Go to a URL, back, forward or reload |
save_profile | Persist the current persona and profile |
get_cdp_endpoint | Return the CDP URL for a raw client |
Plus scrolling, waiting, tab management, cookie and localStorage control, and profile management.
What people use it for
Research with a real browser
Let the model read pages that need JavaScript to render, instead of a text-only fetch.
Routine web chores
Sign-ups, settings pages and dashboards you'd otherwise click through by hand.
Debugging with an assistant
Ask Cursor to reproduce a bug on your staging site and screenshot each step.
Prototyping an automation
Walk through a flow with the model, then take the CDP endpoint and script it.
Clearcote is built for privacy, testing, research and lawful automation. You're responsible for how you use it and for following the terms of the sites you visit.
Which plan includes it
The MCP server is free in every tier. It runs the open build unless you set CLEARCOTE_LICENSE_KEY; a free GitHub key runs the latest build, one browser at a time.
FAQ
Which MCP clients does it work with?
Clients that launch MCP servers from a config file. Claude Desktop is shown above, and Cursor and Cline use the same shape.
Does the model control the fingerprint?
No. The identity comes from environment variables when the server starts, and no tool changes it. That keeps the persona consistent for the whole session and keeps the tool list short.
Do I need Node or Python?
One of them. With Node, npx -y clearcote-mcp downloads and runs the server with no install step. With Python, pip install clearcote-mcp.
What's the difference from the in-browser agent?
The MCP server lets an outside model (the one in your chat client) drive the browser through tools. The in-browser agent runs inside the browser and calls a model endpoint you configure. Both drive the same engine.
Can a script take over the agent's session?
Yes. get_cdp_endpoint returns the CDP URL of the browser the agent is using, and Playwright or Puppeteer can attach to it.
Go deeper in the docs
Related features
Give browser-use, Stagehand, Crawl4AI or your own agent a Chromium with engine-level identity, or run Clearcote's opt-in in-browser agent with your own model.
Run Clearcote as a standing CDP endpoint from the official Docker image, serve() or a CLI, and attach any framework with no code change.
Start a Clearcote browser in the cloud with one API call and connect Playwright or Puppeteer over CDP. Residential IP included, billed per GB of traffic.
Canvas, WebGL, WebGPU, audio, fonts, screen, hardware and locale set in the C++ engine from one seed, so every surface agrees with every other.
Related reading
Try Clearcote
Open source, a drop-in for Playwright & Puppeteer, and coherent down to the TLS handshake.
Free for one browser with GitHub. No card.