Unstructured Document Processor MCP

🚀 Model Context Protocol (MCP) Server for Unstructured Document Processing

This server enables Large Language Models (LLMs) to extract and utilize content from unstructured documents.

⚠️ Important Note

This repository is under development. Use it with caution :)

✨ Features

• Wide File Type Support: Supports a variety of file types, including but not limited to text, image, spreadsheet, presentation, and document formats.

Supported file types:

{".abw", ".bmp", ".csv", ".cwk", ".dbf", ".dif", ".doc", ".docm", ".docx", ".dot",
 ".dotm", ".eml", ".epub", ".et", ".eth", ".fods", ".gif", ".heic", ".htm", ".html",
 ".hwp", ".jpeg", ".jpg", ".md", ".mcw", ".mw", ".odt", ".org", ".p7s", ".pages",
 ".pbd", ".pdf", ".png", ".pot", ".potm", ".ppt", ".pptm", ".pptx", ".prn", ".rst",
 ".rtf", ".sdp", ".sgl", ".svg", ".sxg", ".tiff", ".txt", ".tsv", ".uof", ".uos1",
 ".uos2", ".web", ".webp", ".wk2", ".xls", ".xlsb", ".xlsm", ".xlsx", ".xlw", ".xml",
 ".zabw"}

📦 Installation

Prerequisites

You need the following:

• An Unstructured API key. Learn how to obtain it here
• Claude Desktop installed locally

🚀 Quick Start

Follow these steps to add this MCP to your Claude Desktop:

1. Clone the repository and set up the UV environment.
2. Create a .env file in the root directory and add the following environment variable: UNSTRUCTURED_API_KEY.
3. Run the MCP server: uv run doc_processor.py
4. Navigate to ~/Library/Application Support/Claude/ and create a claude_desktop_config.json file. Add the following content to the file:

{
    "mcpServers": {
        "unstructured_doc_processor": {
            "command": "YOUR UV PATH",
            "args": [
                "--directory",
                "ABSOLUTE PATH TO YOUR unstructured-mcp/",
                "run",
                "doc_processor.py"
            ],
            "disabled": false
        }
    }
}

5. Restart Claude Desktop. You should now be able to use this MCP.