Co-browse with your AI as you edit code. A headed Playwright-controlled browser with accompanying MCP server.
Browse Together MCP MCP server exists for a simple reason — assistants are far more useful when they can act on Browse Together MCP directly instead of describing what you should do. Co-browse with your AI as you edit code. A headed Playwright-controlled browser with accompanying MCP server.
A Playwright browser and MCP Server on your desktop. You can spin up a headful browser (for human interaction) and an accompanying MCP server that can be used to control the browser via HTTP API or MCP server.
The server ships on npm as playwright, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
Once Browse Together MCP is connected, these are the calls the assistant has available:
goto — Navigate to a URLclick — Click on an elementfill — Fill a form fieldcontent — Get the page HTML contentfetch — Execute a fetch request in the browser contextlistPages — List all active browser pagesclosePage — Close a specific pageFeatures — Note: Currently supports Mac OS, but can be extended to other platforms with minor changesYou will need one environment variable: PORT. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
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. Browse Together MCP's toolset — goto, click, fill and 5 more — is a fair guide to whether it matches your workflow. It is maintained by canadaduane; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Browse Together MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| goto | Navigate to a URL |
| click | Click on an element |
| fill | Fill a form field |
| content | Get the page HTML content |
| fetch | Execute a fetch request in the browser context |
| listPages | List all active browser pages |
| closePage | Close a specific page |
| Features | Note: Currently supports Mac OS, but can be extended to other platforms with minor changes. |
{
"mcpServers": {
"browse-together": {
"command": "/path/to/deno",
"args": [
"run",
"--allow-read",
"--allow-net",
"--allow-env",
"--allow-sys",
"/path/to/browse-together-mcp/mcp.ts"
],
"env": {
"PORT": "8888"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| PORT | Configuration value read at startup. | Optional |
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.