Mcphackathon

🚀 Unstructured Content

Unstructured content refers to data without a fixed format, such as text, images, and videos. In the digital age, over 90% of data is unstructured, including emails, documents, and social media posts.

🚀 Quick Start

This guide will introduce you to the processing of unstructured data and how to use Anthropic's MCP (Machine Learning Platform) server to set up and run an unstructured data processing system, integrating it into the Claude desktop environment for further development and debugging.

✨ Features

Introduction

• Unstructured data refers to data without a fixed format, such as text, images, and videos.
• In today's digital age, over 90% of data is unstructured, including emails, documents, social media posts, etc.

Characteristics

• High flexibility: Unstructured data can exist in any form, making it easy to store and transmit.
• Difficult to process: Due to the lack of a fixed format, it is difficult to directly use for data analysis and machine learning models.

Processing Methods

1. Data extraction: Use natural language processing (NLP) techniques to extract useful information from text.
2. Data annotation: Add labels or metadata to unstructured data to make it easier to manage.
3. Data transformation: Convert unstructured data into a structured format for further analysis.

Application Scenarios

• Text mining: Extract useful information from a large number of documents.
• Sentiment analysis: Analyze the sentiment tendency in social media posts.
• Image recognition: Identify objects or scenes in images.

📦 Installation

Installation Steps

1. Install dependencies:

   pip install uvicorn python-dotenv
   

2. Run the MCP server:

   uv run python uns_mcp/server.py --host 0.0.0.0 --port 8080
   

Configuration File

• Create a config.json file:

  {
      "mcpServers": {
          "UNS_MCP": {
              "command": "ABSOLUTE/PATH/TO/.local/bin/uv",
              "args": [
                  "--directory",
                  "ABSOLUTE/PATH/TO/YOUR-UNS-MCP-REPO/uns_mcp",
                  "run",
                  "server.py"
              ],
              "env": [
                  "UNSTRUCTURED_API_KEY": "<your key>"
              ]
          }
      }
  }
  

Integration into Claude Desktop

1. Edit the claude_desktop_config.json file:

   # For macOS or Linux:
   code ~/Library/Application\ Support/Claude/claude_desktop_config.json
   
   # For Windows:
   code $env:AppData\Claude\claude_desktop_config.json
   

2. Add the MCP server configuration:

   {
       "mcpServers": {
           "UNS_MCP": {
               "command": "ABSOLUTE/PATH/TO/.local/bin/uv",
               "args": [
                   "--directory",
                   "ABSOLUTE/PATH/TO/YOUR-UNS-MCP-REPO/uns_mcp",
                   "run",
                   "server.py"
               ],
               "env": [
                   "UNSTRUCTURED_API_KEY": "<your key>"
               ]
           }
       }
   }
   

3. Restart the Claude desktop.

Debugging Tools

• Use the MCP Inspector tool to debug/test your MCP server:

  mcp dev uns_mcp/server.py
  

• Set environment variables to record request parameters:

  DEBUG_API_REQUESTS=false
  

💻 Usage Examples

Basic Usage

Server-side operation

# Run the server in one terminal:
uv run python uns_mcp/server.py --host 127.0.0.1 --port 8080

# Or
make sse-server

Client-side operation

# Run the client in another terminal:
uv run python minimal_client/client.py "http://127.0.0.1:8080/sse"
# Or
make sse-client

Advanced Usage

Note: First, use ctrl+c to exit the client, and then shut down the server. Otherwise, the server may hang.

# The above steps are the advanced usage scenarios for the entire system, including installation, configuration, and integration.