mcp-browser-use-tools
The mcp-browser-use-tools package provides a subset of browser-use functionalities as an MCP server, allowing users to create custom agent loops with minimal dependencies.
The mcp-browser-use-tools package is designed to offer a streamlined version of the browser-use functionalities, specifically tailored for those who wish to implement their own agent loops. By exposing only the internal tools, this package allows for greater flexibility and customization without the overhead of the full browser-use agent. This makes it ideal for developers looking to integrate specific browser automation tasks into their applications or workflows. The package supports a variety of tools that cover essential browser interactions, such as navigating web pages, interacting with elements, and extracting content. This focused approach ensures that users have access to the most critical functionalities needed for effective browser automation, while maintaining a lightweight and efficient setup.
Features
- Minimal dependencies for streamlined integration.
- Exposes essential browser automation tools for custom agent loops.
- Supports a wide range of browser interactions.
- Ideal for developers looking to integrate specific browser tasks.
- Lightweight and efficient setup.
MCP Tools
- {'done': 'Marks the completion of a task.'}
- {'search_google': 'Performs a Google search with the specified query.'}
- {'go_to_url': 'Navigates to a specified URL.'}
- {'go_back': 'Navigates back to the previous page.'}
- {'wait': 'Pauses execution for a specified duration.'}
- {'click_element': 'Clicks on a specified element on the page.'}
- {'input_text': 'Inputs text into a specified field.'}
- {'switch_tab': 'Switches to a different browser tab.'}
- {'open_tab': 'Opens a new browser tab.'}
- {'extract_content': 'Extracts content from the current page.'}
- {'scroll_down': 'Scrolls down the page.'}
- {'scroll_up': 'Scrolls up the page.'}
- {'send_keys': 'Sends keystrokes to the browser.'}
- {'scroll_to_text': 'Scrolls to a specified text on the page.'}
- {'get_dropdown_options': 'Retrieves options from a dropdown menu.'}
- {'select_dropdown_option': 'Selects an option from a dropdown menu.'}
Usage with Different Platforms
Node.js
javascript
const mcp = require('mcp-browser-use-tools');
mcp.go_to_url('https://example.com');
mcp.search_google('MCP server');
Python
python
import mcp_browser_use_tools as mcp
mcp.go_to_url('https://example.com')
mcp.search_google('MCP server')
Related MCP Servers
View all browser_automation servers →Fetch
by modelcontextprotocol
A Model Context Protocol server that provides web content fetching capabilities, enabling LLMs to retrieve and process content from web pages.
markdownify-mcp
by zcaceres
Markdownify is a Model Context Protocol (MCP) server that converts various file types and web content to Markdown format.
mcp-playwright
by executeautomation
A Model Context Protocol server that provides browser automation capabilities using Playwright.
playwright-mcp
by microsoft
Playwright MCP is a Model Context Protocol server that provides browser automation capabilities using Playwright, enabling LLMs to interact with web pages through structured accessibility snapshots.
cursor-talk-to-figma-mcp
by sonnylazuardi
This project implements a Model Context Protocol (MCP) integration between Cursor AI and Figma, allowing Cursor to communicate with Figma for reading designs and modifying them programmatically.
firecrawl-mcp-server
by mendableai
Firecrawl MCP Server is a Model Context Protocol server implementation that integrates with Firecrawl for web scraping capabilities.
ai-agent-marketplace-index-mcp
by AI-Agent-Hub
MCP Server for AI Agent Marketplace Index from DeepNLP, allowing AI assistants to search available AI agents by keywords or categories.