#!/usr/bin/env python3
"""
Sample MCP Server for ChatGPT Deep Research Integration

This server implements the Model Context Protocol (MCP) with search and fetch
capabilities designed to work with ChatGPT's deep research feature.
"""

import logging
import os
import sys
from pathlib import Path
from typing import Dict, List, Any
sys.path.append(str(Path(__file__).parent / "src"))
from src.IberleyAI.Tools.IberleyIAPrompt import IberleyIAPrompt
from fastmcp import FastMCP

# Configure logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

server_instructions = """
This MCP server provides search and document retrieval capabilities 
for deep research. Use the search tool to find relevant documents 
based on keywords, then use the fetch tool to retrieve complete 
document content with citations.
"""

def create_server():
    """Create and configure the MCP server with search and fetch tools."""

    mcp = FastMCP(name="IberleyIA MCP Server",
                  instructions=server_instructions)

    @mcp.tool()
    async def search(query: str) -> Dict[str, List[Dict[str, Any]]]:
        """
        Search for legal information in the berleyAI chatbot connection
        
        This tool searches through the vector store to find semantically relevant matches.
        Returns a list of search results with basic information. Use the fetch tool to get 
        complete document content.
        
        Args:
            query: Search query string. Natural language queries work best for semantic search.
        
        Returns:
            Dictionary with 'content' key containing list of matching documents.
            Each result includes type, text.
        """
        if not query or not query.strip():
            return {"content": []}

        response = IberleyIAPrompt.iberley_ia_prompt(query)

        result = {
            "content": [
                {
                "type": "text",
                "text": response
                }
            ]
        }
        return result

    @mcp.tool()
    async def fetch(id: str) -> Dict[str, Any]:
        """
        Search for legal information in the berleyAI chatbot connection given an id for a
        legal document withing a query in natural language
        
        This tool searches through the vector store to find semantically relevant matches.
        Returns a list of search results with basic information. Use the fetch tool to get 
        complete document content.
        
        Args:
            query: Search query string. Natural language queries work best for semantic search.
        
        Returns:
            Dictionary with 'content' key containing list of matching documents.
            Each result includes type, text.
        """
        if not id or not id.strip():
            return {"content": []}

        response = IberleyIAPrompt.iberley_ia_prompt(id)

        result = {
            "content": [
                {
                "type": "text",
                "text": response
                }
            ]
        }
        return result

    return mcp


def main():
    """Main function to start the MCP server."""
    #conection string should be "https://iberley-iberleyia.hf.space/sse"
    server = create_server()

    logger.info("Starting MCP server on 0.0.0.0:7860")
    logger.info("Server will be accessible via SSE transport")

    try:
        server.run(transport="sse", host="0.0.0.0", port=7860)
    except KeyboardInterrupt:
        logger.info("Server stopped by user")
    except Exception as e:
        logger.error(f"Server error: {e}")
        raise


if __name__ == "__main__":
    main()