PDF Extraction MCP Server (Claude Code Fork)

@xraywu

リポジトリ

基本情報

カテゴリ

ファイルとストレージ

トランスポート

stdio

作者

xraywu

PDF Extraction MCP Server について

MCP server to extract contents from a PDF file

PDF Extraction MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "mcp-pdf-extraction-server": {
      "command": "python",
      "args": [
        "-m",
        "venv",
        "venv"
      ]
    }
  }
}

PDF Extraction MCP Server のツール

Extract contents from a local PDF file

概要

What is PDF Extraction MCP Server (Claude Code Fork)?

The PDF Extraction MCP Server (Claude Code Fork) is an MCP server that extracts text content from PDF files. It is a fork of the original server with critical fixes for installing and running with Claude Code CLI.

How to use PDF Extraction MCP Server (Claude Code Fork)?

Clone the repository, install in development mode with pip install -e ., then find the installed command path and add it to Claude Code using claude mcp add pdf-extraction /full/path/to/pdf-extraction. Once added, start a new Claude session and use /mcp to confirm connection; then ask Claude to extract content from a local PDF by specifying the file path and optionally a comma-separated list of pages (e.g., "1-3,-1").

Key features of PDF Extraction MCP Server (Claude Code Fork)

Extracts text from local PDF files
Supports OCR for scanned documents
Optional page selection with comma-separated numbers
Supports negative indexing (e.g., -1 for last page)
Fixed for Claude Code CLI installation
Runnable as a Python module via python -m pdf_extraction

Use cases of PDF Extraction MCP Server (Claude Code Fork)

Extract content from PDFs for analysis or summarization in Claude
Process specific pages (including the last page) from a multi‑page document
Handle scanned documents via OCR within Claude Code
Automate PDF data extraction in MCP‑enabled workflows

よくある質問

What are the required dependencies?

Python 3.11+ and the packages mcp>=1.2.0, pypdf2>=3.0.1, pytesseract>=0.3.10, Pillow>=10.0.0, pydantic>=2.10.1,<3.0.0, and pymupdf>=1.24.0.

How do I add the server to Claude Code?

After installing, run `which pdf-extraction` to get the full path, then execute `claude mcp add pdf-extraction /full/path/to/pdf-extraction`.

Does this fork work with Claude Desktop?

No, this fork is specifically for Claude Code CLI. For Claude Desktop, refer to the original repository.

What does the extract-pdf-contents tool accept?

It requires a `pdf_path` string (local file path

「ファイルとストレージ」の他のコンテンツ

Rust MCP Filesystem

rust-mcp-stack

Blazing-fast, asynchronous MCP server for seamless filesystem operations.

163

mcp-v8: V8 JavaScript MCP Server

r33drichards

MCP server that exposes a V8 JavaScript runtime as a tool for AI agents like Claude and Cursor. Supports persistent heap snapshots via S3 or local filesystem, and is ready for integration with modern AI development environments.

PDF Reader MCP Server (@shtse8/pdf-reader-mcp)

shtse8

📄 The PDF intelligence layer for AI agents — Agent Document Twin, evidence-first extraction, visual crops, OCR provenance, trust reports, and benchmark-gated releases. MCP server for Claude, Cursor, VS Code, and any MCP client.

810