PDF Reader
Provides an MCP server to extract and process text content from PDF documents, converting it to Markdown format.
About
The PDF Reader is a Model Context Protocol (MCP) server designed to simplify working with PDF documents. It integrates Docling for robust document conversion and text extraction, enabling the transformation of PDF content into clean Markdown. This tool enhances accessibility to local PDF files by offering capabilities for document discovery and efficient text retrieval, making it ideal for integration into various MCP-compatible clients and workflows.
Key Features
- Discovers and lists available PDF files
- Provides `get_document_list` tool
- 1 GitHub stars
- Provides `get_document_text` tool
- MCP Server for PDF processing
- Extracts PDF content to clean Markdown format
Use Cases
- Integrating PDF text extraction into MCP-compatible applications
- Programmatically accessing and processing content from local PDF files
- Enabling direct PDF document interaction within IDEs like VSCode/Cursor
Advertisement