mcp pdf extraction server

Local 2025-09-01 00:40:11 0

Research and Data @xraywu/mcp-pdf-extraction-server

An MCP server that provides a tool to extract text content from local PDF files, supporting both standard PDF reading and OCR capabilities with optional page selection.

MCP server to extract contents from a PDF file

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, representing the local file path of the PDF file - Takes "pages" as an optional string argument, representing the page numbers to extract contents from the PDF file. Page numbers are separated in comma, and negative page numbers supported (e.g. '-1' means the last page) - Supports PDF file reader and OCR

Quickstart

Install

Claude Desktop

On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json

Development/Unpublished Servers Configuration

"mcpServers": {
  "pdf_extraction": {
    "command": "uv",
    "args": [
      "--directory",
      "/Users/xraywu/Workspace/pdf_extraction",
      "run",
      "pdf_extraction"
    ]
  }
}

Published Servers Configuration

"mcpServers": {
  "pdf_extraction": {
    "command": "uvx",
    "args": [
      "pdf_extraction"
    ]
  }
}

[
  {
    "description": "Extract contents from a local PDF file, given page numbers separated in comma. Negative page index number supported.",
    "inputSchema": {
      "properties": {
        "pages": {
          "type": "string"
        },
        "pdf_path": {
          "type": "string"
        }
      },
      "required": [
        "pdf_path"
      ],
      "type": "object"
    },
    "name": "extract-pdf-contents"
  }
]