teslamate-mcp

Instructions

Implementation Reference

• main.py:22-28 (handler)

  Factory that creates the handler function for the tool, which executes the associated SQL query ('battery_health_summary.sql') synchronously using the database manager.
  def create_tool_handler(sql_file: str): """Factory function to create tool handlers""" def handler() -> List[Dict[str, Any]]: return db_manager.execute_query_sync(sql_file) return handler
• main.py:31-39 (registration)

  Dynamically creates and registers the tool handler for 'get_battery_health_summary' (and others) with the FastMCP server.
  # Register all tools from definitions for tool_def in TOOL_DEFINITIONS: tool_func = create_tool_handler(tool_def.sql_file) tool_func.__doc__ = tool_def.description tool_func.__name__ = tool_def.name # Register the tool with the MCP server mcp.tool()(tool_func)
• src/tools.py:37-41 (registration)

  ToolDefinition that registers 'get_battery_health_summary' with its description and SQL file path.
  ToolDefinition( name="get_battery_health_summary", description="Get the battery health summary for each car. Provides current battery health status and statistics.", sql_file="battery_health_summary.sql", ),
• main_remote.py:118-127 (handler)

  Handler function for predefined tools in the remote HTTP server, which loads the ToolDefinition and executes the SQL query asynchronously.
  async def execute_predefined_tool(tool_name: str) -> List[Dict[str, Any]]: """Execute a predefined tool by name""" if not app_context: raise RuntimeError("Application context not initialized") tool = get_tool_by_name(tool_name) return await app_context.db_manager.execute_query_async( tool.sql_file, app_context.db_pool )
• main_remote.py:179-186 (schema)

  Defines the input schema (empty object, no parameters) and registers the tool in the list_tools() for the remote server.
  for tool_def in TOOL_DEFINITIONS: tools.append( types.Tool( name=tool_def.name, description=tool_def.description, inputSchema={"type": "object", "properties": {}}, ) )