IPL MCP Server

Instructions

Implementation Reference

• src/mcp_server/server.py:54-68 (handler)

  Tool call handler in the MCP server that routes 'query_ipl_data' to the QueryEngine.

  @self.server.call_tool()
  async def handle_call_tool(name: str, arguments: Dict[str, Any]) -> List[TextContent]:
      """Handle tool calls"""
      if name == "query_ipl_data":
          query = arguments.get("query", "")
          if not query:
              return [TextContent(type="text", text="Please provide a query.")]
          
          try:
              result = self.query_engine.process_query(query)
              return [TextContent(type="text", text=result)]
          except Exception as e:
              return [TextContent(type="text", text=f"Error processing query: {str(e)}")]
      
      return [TextContent(type="text", text=f"Unknown tool: {name}")]

• src/mcp_server/query_engine.py:111-133 (handler)

  The core logic that parses the query using regex patterns and dispatches it to the appropriate data handling method.

  def process_query(self, query: str) -> str:
      """Process natural language query and return formatted results"""
      query_lower = query.lower().strip()
      
      # Try to match query patterns
      for pattern_info in self.query_patterns:
          pattern = pattern_info['pattern']
          handler = pattern_info['handler']
          
          match = re.search(pattern, query_lower)
          if match:
              try:
                  # Extract parameters from regex groups if any
                  groups = match.groups()
                  params = [g.strip() if g else None for g in groups if g and g.strip()]
                  
                  result = handler(*params) if params else handler()
                  return self.format_result(result, pattern_info['description'])
              except Exception as e:
                  return f"Error executing query: {str(e)}"
      
      # If no pattern matches, try to handle as a general query
      return self.handle_general_query(query)

• src/mcp_server/server.py:26-51 (schema)

  Tool definition, including schema and description.

  Tool(
      name="query_ipl_data",
      description="""Query IPL cricket data using natural language. 
      Examples:
      - 'Show me all matches in the dataset'
      - 'Which team won the most matches?'
      - 'Who scored the most runs across all matches?'
      - 'What was the highest total score?'
      - 'Show matches played in Mumbai'
      - 'Who has the best bowling figures?'
      - 'Show me Virat Kohli batting stats'
      - 'What's the average first innings score?'
      - 'Show me all centuries scored'
      - 'Which venue has the highest scoring matches?'
      """,
      inputSchema={
          "type": "object",
          "properties": {
              "query": {
                  "type": "string",
                  "description": "Natural language query about IPL cricket data"
              }
          },
          "required": ["query"]
      }
  )