MCP server for BabelWrap — give AI agents web browsing superpowers.
If you already use Babelwrap, the babelwrap mcp server is the piece that lets your assistant work with it directly. MCP server for BabelWrap — give AI agents web browsing superpowers.
Works with Claude Desktop, Cursor, Claude Code, and any MCP-compatible client.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
babelwrap_new_session — Create a new browser sessionbabelwrap_close_session — Close a browser sessionbabelwrap_navigate — Navigate to a URLbabelwrap_snapshot — Get current page statebabelwrap_click — Click an elementbabelwrap_fill — Fill a form fieldbabelwrap_submit — Submit a formbabelwrap_extract — Extract structured datababelwrap_screenshot — Take a screenshotbabelwrap_press — Press a keyboard keybabelwrap_scroll — Scroll the pagebabelwrap_hover — Hover over an elementInstallation goes through your MCP client rather than a global install: point it at babelwrap-mcp on PyPI and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
Configuration is passed through the environment: BABELWRAP_API_KEY, BABELWRAP_API_URL. 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.
Among the browser automation options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Babelwrap's toolset — babelwrap_new_session, babelwrap_close_session, babelwrap_navigate and 11 more — is a fair guide to whether it matches your workflow. It is maintained by babelwrap; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| babelwrap_new_session | Create a new browser session |
| babelwrap_close_session | Close a browser session |
| babelwrap_navigate | Navigate to a URL |
| babelwrap_snapshot | Get current page state |
| babelwrap_click | Click an element |
| babelwrap_fill | Fill a form field |
| babelwrap_submit | Submit a form |
| babelwrap_extract | Extract structured data |
| babelwrap_screenshot | Take a screenshot |
| babelwrap_press | Press a keyboard key |
| babelwrap_scroll | Scroll the page |
| babelwrap_hover | Hover over an element |
| babelwrap_upload | Upload a file |
| babelwrap_wait_for | Wait for a condition |
{
"mcpServers": {
"babelwrap": {
"command": "uvx",
"args": ["babelwrap-mcp"],
"env": {
"BABELWRAP_API_KEY": "your-value",
"BABELWRAP_API_URL": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| BABELWRAP_API_KEY | Credential the server authenticates with. | Yes |
| BABELWRAP_API_URL | Endpoint or connection string the server talks to. | 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.