Document & Browser Tools

About

This lightweight server implements the Model Context Protocol (MCP) to extend the capabilities of clients like VS Code Copilot. It specializes in document processing by converting DOCX files to Markdown, preserving formatting, and extracting images without heavy browser dependencies. Additionally, the server provides robust browser automation features, allowing users to open browser windows, navigate to URLs, input text into forms, and take screenshots, making it a versatile toolkit for content management, data extraction, and interactive web scripting.

Key Features

• Browser automation for opening URLs, inputting text, and form submission
• 0 GitHub stars
• Image metadata reading and directory analysis
• JSON-RPC over stdio for standard MCP protocol communication
• Embedded image extraction and handling from documents
• DOCX to Markdown conversion with comprehensive formatting preservation

Use Cases

• Enhancing AI assistants like VS Code Copilot with document processing and web interaction capabilities
• Automating document conversion workflows for content creation and management
• Scripting browser actions for data collection, form filling, or web testing