MCP Directory
Back

pdf-mcp

by jztan · Python · ★ 69

An MCP server that lets Claude Code and other AI agents work through large PDFs without overflowing their context — search by meaning or keyword, read only the pages that matter, and cleanly pull out tables, images, and scanned text, even from multi-column and Japanese layouts.

#agentic-ai#ai#cjk#claude#codex-cli#copilot#document-processing#llm#mcp#mcp-server#model-context-protocol#ocr#opencode#pdf#pdf-extraction#pymupdf#python#semantic-search#table-extraction

Install

pip install git+https://github.com/jztan/pdf-mcp.git

Auto-generated from the repo's primary language — check the repo's own README for its exact install instructions.

Claude Desktop config

A starting point for your claude_desktop_config.json (auto-generated — the repo's README may specify a published package name or required env vars):

{
  "mcpServers": {
    "pdf-mcp": {
      "command": "uvx",
      "args": [
        "git+https://github.com/jztan/pdf-mcp.git"
      ]
    }
  }
}

From the README

[](https://pypi.org/project/pdf-mcp/) [](https://www.python.org/downloads/) [](https://opensource.org/licenses/MIT) [](https://github.com/jztan/pdf-mcp/issues) [](https://github.com/jztan/pdf-mcp/actions/workflows/ci.yml) [](https://codecov.io/gh/jztan/pdf-mcp) [](https://pepy.tech/project/pdf-mcp) **Surgical PDF access for AI agents — search, read, and extract without flooding context.** An [MCP](https://modelcontextprotocol.io/) server that lets Claude Code and other AI agents search a PDF by meaning or keyword, read only the pages that matter, and cleanly pull out tables, images, and scan…
Read full README on GitHub →

Related ai & ml servers