A sophisticated browser automation tool that leverages your actual Chrome profile and authenticated sessions via a local MCP server.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install browsermcp
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install browsermcp using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is BrowserMCP Skill?
The BrowserMCP skill allows AI agents to interact with the web through a user's existing browser instance rather than an isolated, headless environment. By utilizing these Openclaw Skills, developers can perform tasks on websites where they are already logged in, effectively bypassing common bot detection and CAPTCHAs thanks to a real browser fingerprint. This skill maintains privacy by keeping all browser activity local to the device while providing high-speed automation without network latency.
BrowserMCP Skill Use Cases
- Automating repetitive tasks on authenticated platforms like dashboards or internal tools.
- Scraping data from websites that require active user sessions or complex login flows.
- Testing web application UI/UX within a real-world browser environment.
- Filling and submitting complex multi-step forms using stored browser data.
How BrowserMCP Skill Works
- The user starts the BrowserMCP server locally and connects the target tab via the Chrome extension.
- The agent uses the navigate tool to reach a specific URL within the connected tab.
- The agent takes a snapshot to generate an ARIA accessibility tree, which provides unique references for interactive elements.
- Interactions such as click, type, or hover are executed using the exact references identified in the snapshot.
- The agent verifies the result by capturing screenshots or checking JavaScript console logs for errors.
BrowserMCP Skill Setup
To get started with these Openclaw Skills, you must have both the local server and the Chrome extension installed.
- Install and run the BrowserMCP server:
npx @browsermcp/server
- Install the Browser MCP extension from the Chrome Web Store.
- Open the target tab in Chrome and click the extension icon to select Connect.
BrowserMCP Skill Data Schema & Taxonomy
The skill interacts with the browser DOM and returns data primarily through accessibility trees and visual captures.
| Data Type | Description |
|---|---|
| ARIA Snapshot | A structural map of the page using accessibility labels and unique ref IDs. |
| Screenshots | PNG image data representing the current visual state of the browser tab. |
| Console Logs | A collection of recent JavaScript environment logs and errors. |
| Element Refs | Short, unique identifiers (e.g., e12) used to target specific DOM elements accurately. |
BrowserMCP Skill Advanced Features
- Uses existing browser profiles to maintain active login sessions across automation runs.
- Stealth capabilities that utilize real browser fingerprints to avoid basic bot detection.
- Interactive ARIA tree snapshots for precise element targeting without complex CSS selectors.
- Real-time visual verification through automated screenshot capture at any step.
- Access to browser console logs for deep debugging of dynamic web applications.
SKILL.md
Loading
Related Openclaw Skills
OpenClaw Voice
A CLI-driven voice interface for AI agents utilizing Whisper for transcription and ElevenLabs for high-quality speech synthesis.
Orchestration Skill
A robust framework for multi-agent task delegation using a shared SQLite queue and Markdown interchange files for transparent workflow management.
Monitoring Skill
A comprehensive system health utility that monitors token expenditure, task success rates, and cron reliability for AI agent operations.
Openclaw Interchange
A foundational library for agent-to-agent communication via structured Markdown files with atomic safety and deterministic serialization.
Fast Playwright Browser Automation
A high-performance browser automation skill for AI agents that prioritizes token optimization and batch execution.
Typefully Social Media Management
A comprehensive skill for AI agents to manage, schedule, and publish high-quality social media threads and posts via the Typefully API.
Featured*
