pdf-mcp

communitystdiolocalunknownhealthy

MCP server that lets Claude Code and other AI agents work through large PDFs, and whole folders of them, without overflowing context: hybrid semantic + keyword search, selective page reading, tables, images, OCR, chart data, and multi-column/CJK layouts.

Is it safe?Setup guide Alternatives Claim this server

01Tools · 0

Tools require a live tools/list handshake. For local/stdio servers that runs in a sandbox (gated off until configured); remote servers are probed directly.

02Install & source

uvx pdf-mcp

uvx

repohttps://github.com/jztan/pdf-mcp
homepagehttps://pdf-mcp.jztan.com
licenseMIT
adoption136 stars · 14 forks

05Provenance & freshness

sourcesGitHub repo search [p4]

last_checked2026-09-20 15:10Z

next_check2026-09-20 18:10Z

cadenceevery 3h

verifiedmetadata:passed metadata:passed metadata:passed metadata:passed metadata:passed metadata:passed metadata:passed metadata:passed metadata:passed metadata:passed

index_statusindex — 7 unique facts >= 5

06Badge

Add the “as seen on MCPExplorer” badge to your README.

[![pdf-mcp MCP — as seen on mcpexplorer.com](https://mcpexplorer.com/badge/pdf-mcp.svg)](https://mcpexplorer.com/servers/pdf-mcp)

Next step

This is one server. A loadout combines the right servers, governance, and proven plays for a whole job — assembled deliberately, not tool-dumped.

Explore loadouts →