MCP server for remote browser automation using BrowserCat
MCP server for remote browser automation using BrowserCat. That is what the browsercat mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.
A Model Context Protocol server that provides browser automation capabilities using BrowserCat's cloud browser service. This server enables LLMs to interact with web pages, take screenshots, and execute JavaScript in a real browser environment without needing to install browsers locally.
Configuration on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.
The server publishes 11 tools. What each one is for:
browsercat_navigate — Navigate to any URL in the browserInput — url (string)browsercat_screenshot — Capture screenshots of the entire page or specific elementsInputs — - name (string, required): Name for the screenshotbrowsercat_click — Click elements on the pagebrowsercat_hover — Hover elements on the pagebrowsercat_fill — Fill out input fieldsbrowsercat_select — Select an option from a dropdown menubrowsercat_evaluate — Execute JavaScript in the browser consoleTools — The Tools tool exposed by this serverResources — 1. Console Logs (console://logs) - Browser console output in text format - Includes all console messages from the browser 2. ScreenshotsConfiguration is passed through the environment: BROWSERCAT_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
This sits in the browser automation group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Browsercat's toolset — browsercat_navigate, Input, browsercat_screenshot and 8 more — is a fair guide to whether it matches your workflow. It is maintained by dmaznest; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| browsercat_navigate | Navigate to any URL in the browser |
| Input | url (string) |
| browsercat_screenshot | Capture screenshots of the entire page or specific elements |
| Inputs | - name (string, required): Name for the screenshot |
| browsercat_click | Click elements on the page |
| browsercat_hover | Hover elements on the page |
| browsercat_fill | Fill out input fields |
| browsercat_select | Select an option from a dropdown menu |
| browsercat_evaluate | Execute JavaScript in the browser console |
| Tools | The Tools tool exposed by this server. |
| Resources | 1. **Console Logs** (console://logs) - Browser console output in text format - Includes all console messages from the browser 2. **Screenshots** (screenshot://<name>) - PNG images of captured screenshots - Accessible via |
{
"mcpServers": {
"browsercat": {
"command": "npx",
"args": ["-y", "@browsercatco/mcp-server"],
"env": {
"BROWSERCAT_API_KEY": "your-api-key-here"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| BROWSERCAT_API_KEY | Credential the server authenticates with. | Yes |
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
Industrial-strength web extraction — render, scrape, crawl and search entire sites into clean markdown.
The original Chromium automation reference server — simple, screenshot-driven browser control.
Give your coding agent the full DevTools toolbox: traces, network, console, heap snapshots and Lighthouse.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Cloud browsers for AI agents — automation sessions that run in Browserbase's fleet, not on your machine.