Happy slice of mcp pizzaMCP.pizza

mcp-pdf-extraction-server

MCP.Pizza Chef: xraywu

The mcp-pdf-extraction-server is an MCP server designed to extract contents from local PDF files efficiently. It supports both direct PDF text reading and OCR for scanned documents, allowing extraction from specified pages or the entire document. This server enables seamless integration of PDF content extraction into AI workflows, enhancing document analysis, data retrieval, and automation tasks. It accepts a file path and optional page numbers, including negative indices for flexible page targeting.

Unmaintained · No commits in 15 months.

Use This MCP server To

Extract text from specific pages of local PDF files Perform OCR on scanned PDF documents Integrate PDF content extraction into AI workflows Automate data retrieval from PDF reports Enable document analysis in AI-powered applications

README

PDF Extraction MCP Server (Claude Code Fork)

MCP server to extract contents from PDF files, with fixes for Claude Code CLI installation.

This fork includes critical fixes for installing and running the server with Claude Code (the CLI version).

What's Different in This Fork

  1. Added __main__.py - Enables the package to be run as a module with python -m pdf_extraction
  2. Claude Code specific instructions - Clear installation steps that work with Claude Code CLI
  3. Tested installation process - Verified working with claude mcp add command

Components

Tools

The server implements one tool:

  • extract-pdf-contents: Extract contents from a local PDF file
    • Takes pdf_path as a required string argument (local file path)
    • Takes pages as an optional string argument (comma-separated page numbers, supports negative indexing like -1 for last page)
    • Supports both PDF text extraction and OCR for scanned documents

Installation for Claude Code CLI

Prerequisites

  • Python 3.11 or higher
  • pip or conda
  • Claude Code CLI installed (claude command)

Step 1: Clone and Install

mcp-pdf-extraction-server FAQ

How do I specify which pages to extract from a PDF?
Use the 'pages' argument with comma-separated page numbers; negative numbers count from the end (e.g., '-1' for last page).
Can this server extract text from scanned PDFs?
Yes, it supports OCR to extract text from scanned or image-based PDFs.
What argument is required to extract PDF contents?
The 'pdf_path' argument specifying the local file path of the PDF is required.
How do I install the mcp-pdf-extraction-server for Claude Desktop?
Add the server configuration to the claude_desktop_config.json file located in the user application support directory on MacOS or Windows.
Does the server support extraction from remote PDF files?
No, it currently supports extraction only from local PDF files specified by path.
Is the server compatible with multiple LLM providers?
Yes, it can be integrated with models from OpenAI, Anthropic Claude, and Google Gemini via MCP clients.
Can I extract content from multiple pages at once?
Yes, specify multiple pages separated by commas in the 'pages' argument.
What happens if I omit the 'pages' argument?
The server extracts content from all pages of the PDF by default.