PDF Knowledgebase
byjuanqui
0Enables intelligent document search and retrieval from PDF collections by serving as a Model Context Protocol (MCP) server.
About
PDF Knowledgebase is a Model Context Protocol (MCP) server designed to transform collections of PDF documents into a searchable knowledge base. It provides intelligent document search and retrieval capabilities by leveraging OpenAI embeddings and ChromaDB for vector storage. Built for seamless integration, it allows users to semantically query their PDF content directly from popular MCP clients like Claude Desktop, VS Code (Continue), and Cline, enhancing contextual understanding and information access.
Key Features
- Comprehensive Document Management Tools (Add, Search, List, Remove Documents)
- 0 GitHub stars
- Semantic Search and Retrieval for PDF Documents
- Seamless Integration with MCP Clients (Claude Desktop, VS Code, Continue)
- Configurable PDF Parsers (e.g., Marker, PyMuPDF4LLM, MinerU, Docling, LLM)
- Utilizes OpenAI Embeddings and ChromaDB for Vector Storage
Use Cases
- Enhancing AI assistant capabilities with domain-specific content from PDF files
- Optimizing PDF parsing and search for specialized documents like academic papers or business reports
- Transforming personal or organizational PDF document collections into a searchable knowledge base