restore

README.md

@@ -1,49 +1,102 @@
-# ExposureGPT - Manual Upload v2 (Progress Indicators)
+---
+title: ExposureGPT
+emoji: 🎯
+colorFrom: blue
+colorTo: purple
+sdk: gradio
+sdk_version: "5.0.0"
+app_file: app.py
+pinned: false
+license: mit
+short_description: Simplified OSINT Intelligence Platform with MCP Support
+---
 
-## NEW: Native Progress Indicators ✨
+# 🎯 ExposureGPT - Simplified OSINT Intelligence
 
-This version includes native Gradio progress indicators showing real-time status:
-- "Agent working now..."
-- "🤖 LLM interpreting input..."
-- "🔍 Checking OSINT data..."
-- "🧠 AI generating security analysis..."
-- "📋 Compiling intelligence report..."
-- "✅ Intelligence gathering complete!"
+**Single MCP tool for comprehensive security intelligence using Shodan + OpenAI**
 
-Users now see exactly what's happening and won't repeatedly click the button!
+[![🚀 Live on HuggingFace](https://img.shields.io/badge/🚀-Live%20on%20HuggingFace-blue)](https://huggingface.co/spaces/ACloudCenter/ExposureGPT)
+[![MCP Server](https://img.shields.io/badge/🤖-MCP%20Server-green)](https://huggingface.co/spaces/ACloudCenter/ExposureGPT)
 
-## Files for HuggingFace Spaces Upload
+## 🚀 Features
 
-1. **app.py** - HuggingFace Spaces entry point
-2. **exposuregpt_simple.py** - Main application with progress indicators
-3. **requirements.txt** - Dependencies for HF Spaces
-4. **README.md** - This file
+- **Single Tool**: One comprehensive OSINT intelligence gathering function
+- **Shodan Integration**: Real infrastructure and device discovery
+- **AI Analysis**: GPT-4o-mini powered security insights
+- **MCP Server**: Built-in Model Context Protocol server for AI assistants
+- **Risk Assessment**: Automated security scoring and recommendations
+- **Simple Interface**: Single input, comprehensive output
 
-## HuggingFace Spaces Setup
+## 🔧 Configuration
 
-1. Upload all 4 files to your HuggingFace Space
-2. Set Repository Secrets:
-   - `OPENAI_API_KEY` = your OpenAI API key
-   - `SHODAN_API_KEY` = your Shodan API key
-3. Space will auto-rebuild and deploy
+⚠️ **Required**: Set these environment variables in your Space settings:
 
-## MCP Endpoint
+- `SHODAN_API_KEY` - Your Shodan API key (get from https://shodan.io)
+- `OPENAI_API_KEY` - Your OpenAI API key (get from https://openai.com)
 
-Once deployed, your MCP endpoint will be:
+## 🤖 MCP Integration
+
+This Space automatically serves as an MCP server that AI assistants like Claude can use!
+
+**MCP Endpoint**: `https://acloudcenter-exposuregpt.hf.space/gradio_api/mcp/sse`
+
+**Claude Desktop Configuration**:
+```json
+{
+  "mcpServers": {
+    "exposuregpt": {
+      "command": "npx",
+      "args": ["mcp-remote", "https://acloudcenter-exposuregpt.hf.space/gradio_api/mcp/sse"]
+    }
+  }
+}
+```
+
+## 📊 Available Tool
+
+**`intelligence_gathering(target: str)`**
+- Comprehensive OSINT analysis for any domain, IP address, or organization
+- Uses Shodan for infrastructure discovery and vulnerability detection  
+- AI-powered analysis with actionable security recommendations
+- Returns detailed security report with risk assessment
+
+## 💡 Usage Examples
+
+### Web Interface
+- **Domain**: `google.com` - Analyze domain infrastructure
+- **IP Address**: `8.8.8.8` - Scan specific IP for services  
+- **Organization**: `Microsoft Corp` - Corporate intelligence gathering
+
+### Via AI Assistant (Claude)
 ```
-https://your-username-spacename.hf.space/gradio_api/mcp/sse
+"Analyze the security posture of example.com"
+"What are the security risks for tesla.com?"
+"Perform OSINT analysis on 1.1.1.1"
 ```
 
-## What's New in v2
+## 🛡️ Security & Ethics
+
+This tool is designed for:
+- ✅ Security awareness and education
+- ✅ Authorized penetration testing
+- ✅ Risk assessment for your own organization
+- ✅ Academic research
+
+**Not for:**
+- ❌ Unauthorized reconnaissance
+- ❌ Malicious activities
+- ❌ Privacy violations
+
+## 🔍 How It Works
 
-- ✅ Native Gradio progress indicators
-- ✅ Real-time status updates during analysis
-- ✅ Better user experience (no more button mashing!)
-- ✅ Same powerful OSINT + LLM analysis
-- ✅ Full MCP server compatibility
+1. **Input Analysis**: Automatically detects if target is domain, IP, or organization
+2. **Shodan Query**: Searches for exposed infrastructure and services
+3. **Risk Assessment**: Analyzes vulnerabilities and calculates risk scores
+4. **AI Analysis**: GPT-4o-mini generates security insights and recommendations
+5. **Comprehensive Report**: Formatted intelligence report with actionable findings
 
-## Working Example
+Perfect for security researchers, penetration testers, and AI assistants needing OSINT capabilities.
 
-Live at: https://acloudcenter-exposuregpt.hf.space
+---
 
-Enjoy the enhanced user experience! 🚀
+*Built for the 2025 Gradio Agents & MCP Hackathon*

app.py

@@ -0,0 +1,20 @@
+#!/usr/bin/env python3
+"""
+ExposureGPT - HuggingFace Spaces App
+Simplified OSINT Intelligence Platform with MCP Support
+"""
+
+import os
+import sys
+
+# Set up environment for HuggingFace Spaces
+os.environ.setdefault('GRADIO_SERVER_NAME', '0.0.0.0')
+os.environ.setdefault('GRADIO_SERVER_PORT', '7860')
+
+# Import and run the simplified version
+from exposuregpt_simple import main
+
+if __name__ == "__main__":
+    # Force web mode for HuggingFace Spaces
+    sys.argv = ['app.py', '--port', '7860', '--share']
+    main()

exposuregpt_simple.py

@@ -52,7 +52,7 @@ if OpenAI and OPENAI_API_KEY:
         logger.error(f"❌ OpenAI connection failed: {e}")
 
 
-def intelligence_gathering(target: str, progress=gr.Progress()) -> str:
+def intelligence_gathering(target: str) -> str:
     """
     Comprehensive OSINT intelligence gathering for domains, IPs, or organizations.
     
@@ -67,10 +67,8 @@ def intelligence_gathering(target: str, progress=gr.Progress()) -> str:
     """
     try:
         logger.info(f"🎯 Starting intelligence gathering for: {target}")
-        progress(0, desc="Agent working now...")
         
         # Step 1: LLM interprets and clarifies user input
-        progress(0.1, desc="🤖 LLM interpreting input...")
         interpreted_target = _interpret_user_input(target)
         
         # Check if LLM needs clarification
@@ -82,7 +80,6 @@ def intelligence_gathering(target: str, progress=gr.Progress()) -> str:
             logger.info(f"🤖 LLM interpreted '{target}' as '{interpreted_target}'")
         
         # Step 2: Gather raw intelligence data
-        progress(0.3, desc="🔍 Checking OSINT data...")
         shodan_data = _gather_shodan_intelligence(interpreted_target)
         
         # Check if we have any data to work with
@@ -90,18 +87,15 @@ def intelligence_gathering(target: str, progress=gr.Progress()) -> str:
             return f"❌ Cannot analyze {interpreted_target}: {shodan_data['error']}\n\nPlease configure API keys and try again."
         
         # Step 3: Generate AI-powered analysis
-        progress(0.6, desc="🧠 AI generating security analysis...")
         ai_analysis = _generate_ai_analysis(interpreted_target, shodan_data)
         
         # Step 4: Format comprehensive report
-        progress(0.9, desc="📋 Compiling intelligence report...")
         report = _format_intelligence_report(interpreted_target, shodan_data, ai_analysis)
         
         # Add interpretation note if target was changed
         if interpreted_target != target:
             report = f"🤖 **LLM Interpretation**: Analyzed '{interpreted_target}' based on your query: '{target}'\n\n" + report
         
-        progress(1.0, desc="✅ Intelligence gathering complete!")
         logger.info(f"✅ Intelligence gathering completed for {interpreted_target}")
         return report
         

gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

requirements.txt

@@ -1,12 +1,4 @@
-# Core Dependencies for HuggingFace Spaces
-gradio[mcp]>=5.0.0
-openai>=1.0.0
+gradio[mcp]
+openai
 shodan
-requests
-pandas
-numpy
-beautifulsoup4
-dnspython
-python-dotenv
-pydantic
-cryptography
+python-dotenv