mcp
Browser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser
How to use
The mcp server is a Model Context Provider that facilitates seamless interaction between AI applications and your browser. Developers can leverage this server to control browser actions and manipulate the document context, enabling advanced automation and AI-driven functionalities. Its capabilities allow for dynamic content manipulation, event handling, and context-aware interactions, making it an essential tool for building responsive web applications.
Once connected to the mcp server, you can issue commands to control various aspects of your browser session. You can send queries to retrieve the current DOM context, execute JavaScript directly, or manipulate page elements based on AI-driven decisions. Best results are achieved when using context-aware commands that consider the current state of the page and user interactions, making your AI applications more effective and responsive.
How to install
Prerequisites
Ensure you have Node.js installed on your machine to run the mcp server. You can check your installation by running node -v in your terminal.
Option A: Quick Start with npx
For a quick setup, you can use npx to run the mcp server without installing it globally:
npx -y BrowserMCP/mcp
Option B: Global Install Alternative
If you prefer to install the mcp server globally, you can clone the repository and run the server:
git clone https://github.com/BrowserMCP/mcp.git
cd mcp
npm install
node server.js
Make sure to replace server.js with the actual entry point file if it differs.
Additional notes
When configuring the mcp server, consider setting environment variables to customize its behavior, such as specifying the port or enabling debug mode. A common issue is forgetting to allow the necessary permissions for the server to interact with the browser, so ensure your browser is configured accordingly. Always consult the repository documentation for updates and further configuration options.
Related MCP Servers
Mantic.sh
A structural code search engine for Al agents.
mcp -azure-devops
An MCP server for Azure DevOps
kanban
MCP Kanban is a specialized middleware designed to facilitate interaction between Large Language Models (LLMs) and Planka, a Kanban board application. It serves as an intermediary layer that provides LLMs with a simplified and enhanced API to interact with Planka's task management system.
MCP -Starter
A Model Context Protocol server starter template
mongo
MCP server that provide tools to LLMs such as claude in cursor to interact with MongoDB
zip
An MCP tool that provides AI with the ability to compress and decompress local files.