pdf-mcp
An agentic RAG MCP server that enables AI agents to search and read large PDFs or entire folders. It supports hybrid semantic and keyword search, selective page reading, table extraction, OCR for scanned documents, and handles multi-column and CJK layouts. It uses a SQLite cache for repeated access and offers optional CUDA acceleration for faster embedding.
Package and access
Local package with source-attributed installation metadata. Koskamo does not execute packages during review.
What you can do with it
- Search large PDFs using hybrid semantic and keyword methods
- Extract structured tables and chart data from documents
- Perform OCR on scanned PDF pages
- Read specific pages from a folder of PDFs
Source and maintenance
- Maintenance checked
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
https://github.com/jztan/pdf-mcp/releases/download/v3.6.0/pdf-mcp-3.6.0.mcpb
{
"transport": "stdio",
"fileSha256": "c5f440c35e0ab33a5568f4f4a3339974832c66d9e3a1590c067bc79d11650ca9",
"identifier": "https://github.com/jztan/pdf-mcp/releases/download/v3.6.0/pdf-mcp-3.6.0.mcpb",
"registryType": "mcpb"
}Tools
Reported by the attributed source; not independently observed by Koskamo.
Let your agent find its tools
Find servers like pdf-mcp from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.