PDF Model Context Protocol Server

Example Use Cases

• 1

  Read and extract structured content from large PDF documents without context overflow.

• 2

  Perform full-text search within PDFs before loading content.

• 3

  Persistent caching of PDF data to improve performance across sessions.

Description

pdf-mcp is a Python-based MCP server that allows AI agents to efficiently interact with PDF documents by reading, searching, and extracting text, images, tables, and metadata. It supports large PDFs through paginated reading and full-text search, and uses SQLite caching for persistence across server restarts, improving performance and reducing redundant processing. The server offers seven specialized tools tailored for different PDF operations and supports reading PDFs from URLs.