Kapture is a Chrome DevTools Extension that enables browser automation through the Model Context Protocol (MCP). It allows AI applications like
Kapture is a Chrome DevTools Extension that enables browser automation through the Model Context Protocol (MCP). It allows AI applications like Claude to control web browsers via a three-layer architecture. That is what the kapture mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.
Kapture bridges AI assistants with web browsers through: - MCP Server: Handles MCP protocol communication - Chrome Extension: Background service worker executes browser automation commands (DevTools does not need to be open) - WebSocket Bridge: Real-time communication between server and extensions - Multi-Client Support: Multiple AI clients can connect simultaneously via WebSocket
The server publishes 14 tools. What each one is for:
navigate — Navigate to URLback — Browser back buttonforward — Browser forward buttonreload — Reload the current page (similar to pressing F5)click — Click elements (uses first matching element, returns unique selector)hover — Hover over elements (uses first matching element, returns unique selector)fill — Fill input fields by setting value directly (uses first matching element, returns unique selector)type — Type a string as individual keystrokes (real key events; works on "fake" inputs that ignore element.value)insertText — Insert a whole string at once (fires input events but no per-key events; good for bulk text and editors like Google Docs)clear — Clear a text field via select-all + Backspace (real key events; works on "fake" inputs)select — Select dropdown options (HTML only, uses first matching element, returns unique selector)keypress — Send keyboard events to the page or specific elements (supports modifier keys)kapture-mcp on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.
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. Kapture's toolset — navigate, back, forward and 11 more — is a fair guide to whether it matches your workflow. It is maintained by williamkapke; 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 |
|---|---|
| navigate | Navigate to URL |
| back | Browser back button |
| forward | Browser forward button |
| reload | Reload the current page (similar to pressing F5) |
| click | Click elements (uses first matching element, returns unique selector) |
| hover | Hover over elements (uses first matching element, returns unique selector) |
| fill | Fill input fields by setting value directly (uses first matching element, returns unique selector) |
| type | Type a string as individual keystrokes (real key events; works on "fake" inputs that ignore element.value) |
| insertText | Insert a whole string at once (fires input events but no per-key events; good for bulk text and editors like Google Docs) |
| clear | Clear a text field via select-all + Backspace (real key events; works on "fake" inputs) |
| select | Select dropdown options (HTML <select> only, uses first matching element, returns unique selector) |
| keypress | Send keyboard events to the page or specific elements (supports modifier keys) |
| scroll | Scroll an element into view (selector/xpath) or to an absolute x/y document coordinate |
| elements | Query all elements matching a CSS selector or XPath with optional visibility filtering |
{
"mcpServers": {
"kapture": {
"command": "npx",
"args": ["-y", "kapture-mcp@latest", "bridge"]
}
}
}Configuration as documented by the project. Restart the client after saving.
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.