loading…
Search for a command to run...
loading…
MCP browser agent that runs as a Chrome extension. Control your real Chrome browser with 17 MCP tools — uses accessibility tree with @ref labels for low token u
MCP browser agent that runs as a Chrome extension. Control your real Chrome browser with 17 MCP tools — uses accessibility tree with @ref labels for low token usage. Supports WebMCP native tools.
A WebMCP-native browser agent that runs inside your real Chrome — control it from Claude, Cursor, and any MCP client.
| 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 | @ref a11y tree |
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.
Add to claude_desktop_config.json:
{
"mcpServers": {
"webclaw": {
"command": "npx",
"args": ["-y", "webclaw-mcp"]
}
}
}
Config file locations:
~/Library/Application Support/Claude/claude_desktop_config.json~/.config/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.jsonclaude mcp add webclaw -- npx -y webclaw-mcp
Add 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"]
}
}
}
chrome://extensions/ → enable Developer modedist/ foldergit clone https://github.com/kuroko1t/webclaw.git && cd webclaw && pnpm install && pnpm build
Then load packages/extension/dist/ as above.
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.
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:#fff
navigate_to, page_snapshot, click, ...)@ref labels@ref and acts — no pixel coordinates, no CSS selectorspage_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.
| Tool | Parameters | Description |
|---|---|---|
navigate_to |
url, tabId? |
Navigate to a URL |
page_snapshot |
focusRegion?, interactiveOnly?, tabId? |
Get a compact accessibility tree with @ref labels |
click |
ref, snapshotId, tabId? |
Click an element by its @ref label |
hover |
ref, snapshotId, tabId? |
Hover over an element to reveal hidden UI (dropdowns, tooltips) |
type_text |
ref, text, snapshotId, clearFirst?, tabId? |
Type text into an input/textarea by @ref |
select_option |
ref, value, snapshotId, tabId? |
Select a dropdown option by @ref |
drop_files |
ref, snapshotId, files, tabId? |
Drop files onto an element (e.g., upload images to GitHub issues) |
screenshot |
tabId? |
Capture the visible area of the active tab |
handle_dialog |
action, promptText?, tabId? |
Handle a native browser dialog (alert/confirm/prompt) |
evaluate |
expression, tabId? |
Evaluate JavaScript in the page context (e.g., localStorage, cookies, computed styles) |
| Tool | Parameters | Description |
|---|---|---|
new_tab |
url? |
Open a new tab (optionally with a URL) |
list_tabs |
List all open tabs with tabId, URL, title, and active state | |
switch_tab |
tabId |
Switch to a specific tab |
close_tab |
tabId |
Close a specific tab |
| Tool | Parameters | Description |
|---|---|---|
go_back |
tabId? |
Go back to the previous page |
go_forward |
tabId? |
Go forward to the next page |
reload |
tabId?, bypassCache? |
Reload the current page |
wait_for_navigation |
tabId?, timeoutMs? |
Wait for the page to finish loading |
scroll_page |
direction?, amount?, ref?, snapshotId?, tabId? |
Scroll the page or scroll to a specific element |
| Tool | Parameters | Description |
|---|---|---|
list_webmcp_tools |
tabId? |
Discover tools on the page (native WebMCP + auto-synthesized from buttons/forms) |
invoke_webmcp_tool |
toolName, args?, tabId? |
Invoke a discovered tool (native or synthesized) |
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 mode
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 discovery
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.
| Variable | Default | Description |
|---|---|---|
WEBCLAW_PORT |
18080 |
WebSocket port for MCP server ↔ extension communication. When set, disables auto-scanning and uses only this port. |
Chrome extension not connected
chrome://extensions/ → Details → Service Worker) for Connected to MCP serverWebSocket server listening on 127.0.0.1:<port> in stderr)MCP client cannot connect
npx webclaw-mcp runs successfully from your terminalWEBCLAW_PORT to a custom portContent script not injecting
http:// and https:// pages (not chrome://, file://, etc.)WebMCP tools not discovered
navigator.modelContext APInavigator.modelContext.addTool() or <link rel="webmcp-manifest">Contributions are welcome! Please open an issue to discuss your idea before submitting a pull request.
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.
Добавь это в claude_desktop_config.json и перезапусти Claude Desktop.
{
"mcpServers": {
"webclaw-mcp": {
"command": "npx",
"args": []
}
}
}