Enables automated searching and navigation of Wikipedia through a browser-based agent, allowing users to find articles and interact with page content programmatically.
WebClaw
A WebMCP-native browser agent that runs inside your real Chrome — control it from Claude, Cursor, and any MCP client.
Why WebClaw?
WebClaw | browser-use | Playwright MCP | |
Runs in real Chrome | Yes (extension) | No (CDP) | No (Playwright) |
User's logged-in sessions | Yes | No | No |
Bot detection | Resistant | Vulnerable | Vulnerable |
WebMCP native tools | Yes | No | No |
Page understanding |
| Screenshots | DOM / Screenshots |
WebClaw runs as a Chrome extension, so it sees exactly what you see — cookies, logins, extensions, and all. No headless browser, no CDP injection, no bot flags.
Quick Start
1. Configure your MCP client
Add to claude_desktop_config.json:
{
"mcpServers": {
"webclaw": {
"command": "npx",
"args": ["-y", "webclaw-mcp"]
}
}
}Config file locations:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonLinux:
~/.config/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
claude mcp add webclaw -- npx -y webclaw-mcpAdd to .cursor/mcp.json in your project root:
{
"mcpServers": {
"webclaw": {
"command": "npx",
"args": ["-y", "webclaw-mcp"]
}
}
}Add to .vscode/mcp.json in your project root:
{
"servers": {
"webclaw": {
"type": "stdio",
"command": "npx",
"args": ["-y", "webclaw-mcp"]
}
}
}Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"webclaw": {
"command": "npx",
"args": ["-y", "webclaw-mcp"]
}
}
}2. Load the Chrome extension
Download the latest
webclaw-extension.zipfrom the Releases page and unzipOpen
chrome://extensions/→ enable Developer modeClick Load unpacked → select the
dist/folder
git clone https://github.com/kuroko1t/webclaw.git && cd webclaw && pnpm install && pnpm buildThen load packages/extension/dist/ as above.
3. Try it
Restart your MCP client and ask:
"Go to wikipedia.org and search for Model Context Protocol"
Chrome launches automatically on the first tool call. The Side Panel shows all activity in real-time.
How It Works
flowchart LR
LLM["AI Assistant"]
MCP["MCP Server"]
EXT["Chrome Extension"]
CS["Content Script"]
LLM -- "stdio" --> MCP -- "WebSocket" --> EXT --> CS
style LLM fill:#7b2d8b,stroke:#333,color:#fff
style MCP fill:#1a5276,stroke:#333,color:#fff
style EXT fill:#1e8449,stroke:#333,color:#fff
style CS fill:#b7950b,stroke:#333,color:#fffThe AI calls MCP tools (
navigate_to,page_snapshot,click, ...)The MCP server forwards requests to the Chrome extension via WebSocket
The content script reads the page as a compact accessibility tree with
@reflabelsThe AI picks the right
@refand acts — no pixel coordinates, no CSS selectors
page_snapshot output
[page "Wikipedia, the free encyclopedia"]
[search]
[form]
[@e3 searchbox "Search Wikipedia"] ← AI targets this
[@e4 button "Search"] ← and clicks this
[main]
[heading[1] "Welcome to Wikipedia"]
[group]
[heading[2] "From today's featured article"]
...Every interactive element gets a stable @ref label. The AI reads the tree, picks the right @ref, and calls click / type_text / select_option.
MCP Tools (21)
Tool | Parameters | Description |
|
| Navigate to a URL |
|
| Get a compact accessibility tree with |
|
| Click an element by its |
|
| Hover over an element to reveal hidden UI (dropdowns, tooltips) |
|
| Type text into an input/textarea by |
|
| Select a dropdown option by |
|
| Drop files onto an element (e.g., upload images to GitHub issues) |
|
| Capture the visible area of the active tab |
|
| Handle a native browser dialog (alert/confirm/prompt) |
|
| Evaluate JavaScript in the page context (e.g., localStorage, cookies, computed styles) |
Tool | Parameters | Description |
|
| Open a new tab (optionally with a URL) |
| List all open tabs with tabId, URL, title, and active state | |
|
| Switch to a specific tab |
|
| Close a specific tab |
Tool | Parameters | Description |
|
| Go back to the previous page |
|
| Go forward to the next page |
|
| Reload the current page |
|
| Wait for the page to finish loading |
|
| Scroll the page or scroll to a specific element |
Tool | Parameters | Description |
|
| Discover tools on the page (native WebMCP + auto-synthesized from buttons/forms) |
|
| Invoke a discovered tool (native or synthesized) |
Development
git clone https://github.com/kuroko1t/webclaw.git
cd webclaw
pnpm install
pnpm build # Build all packages
pnpm test # Run all tests
pnpm dev # Watch modeProject Structure
packages/
shared/ Type definitions, Zod schemas, utilities
mcp-server/ MCP server with 21 tools, WebSocket bridge
extension/ Chrome MV3 extension (service worker, content scripts, side panel)
examples/
webmcp-demo-site/ WebMCP-enabled Todo app for testing native tool discoveryMulti-Session Support
WebClaw automatically scans ports 18080–18089, so you can run up to 10 MCP server instances simultaneously (e.g., multiple Claude Code sessions). Each instance binds to the first available port, and the Chrome extension connects to all of them.
Environment Variables
Variable | Default | Description |
|
| WebSocket port for MCP server ↔ extension communication. When set, disables auto-scanning and uses only this port. |
Chrome extension not connected
Chrome is auto-launched when a tool is called. If it fails, start Chrome manually with the extension loaded
Check the Service Worker console (
chrome://extensions/→ Details → Service Worker) forConnected to MCP serverVerify the MCP server is running (look for
WebSocket server listening on 127.0.0.1:<port>in stderr)
MCP client cannot connect
Ensure
npx webclaw-mcpruns successfully from your terminalCheck for port conflicts: WebClaw auto-scans 18080–18089. If all are in use, set
WEBCLAW_PORTto a custom portRestart your MCP client after updating the config
Content script not injecting
Content scripts only inject into
http://andhttps://pages (notchrome://,file://, etc.)Try refreshing the page after loading the extension
WebMCP tools not discovered
Native WebMCP requires Chrome 146+ with the
navigator.modelContextAPIVerify the page declares tools via
navigator.modelContext.addTool()or<link rel="webmcp-manifest">
Contributing
Contributions are welcome! Please open an issue to discuss your idea before submitting a pull request.
Disclaimer
WebClaw is a browser automation tool intended for legitimate use cases such as personal productivity, development, testing, and accessibility. Users are responsible for complying with the terms of service of any website they interact with. The authors are not responsible for any misuse of this tool.