AWS Cost Explorer

[DEPRECATED] Analyze what drove cost changes between two time periods. This tool provides detailed analysis of the TOP 10 most significant cost drivers that caused changes between periods. AWS returns only the most impactful drivers to focus on the changes that matter most for cost optimization. The tool provides rich insights including: - Top 10 most significant cost drivers across all services (or filtered subset) - Specific usage types that drove changes (e.g., "BoxUsage:c5.large", "NatGateway-Hours") - Multiple driver types: usage changes, savings plan impacts, enterprise discounts, support fees - Both cost and usage quantity changes with units (hours, GB-months, etc.) - Context about what infrastructure components changed - Detailed breakdown of usage patterns vs pricing changes Can be used with or without filters: - Without filters: Shows top 10 cost drivers across ALL services - With filters: Shows top 10 cost drivers within the filtered scope - Multiple services: Can filter to multiple services and get top 10 within that scope Both periods must be exactly one month and start/end on the first day of a month. Important requirements: - Both periods must be exactly one month duration - Dates must start and end on the first day of a month (e.g., 2025-01-01 to 2025-02-01) - Maximum lookback of 13 months (38 months if multi-year data enabled) - Start dates must be equal to or no later than current date - Results limited to top 10 most significant drivers (no pagination) Example: Analyze top 10 cost drivers across all services await get_cost_comparison_drivers( ctx=context, baseline_date_range={ "start_date": "2024-12-01", # December 2024 "end_date": "2025-01-01" }, comparison_date_range={ "start_date": "2025-01-01", # January 2025 "end_date": "2025-02-01" }, metric_for_comparison="UnblendedCost", group_by={"Type": "DIMENSION", "Key": "SERVICE"} # No filter = top 10 drivers across all services ) Example: Analyze top 10 cost drivers for specific services await get_cost_comparison_drivers( ctx=context, baseline_date_range={ "start_date": "2024-12-01", "end_date": "2025-01-01" }, comparison_date_range={ "start_date": "2025-01-01", "end_date": "2025-02-01" }, metric_for_comparison="UnblendedCost", group_by={"Type": "DIMENSION", "Key": "SERVICE"}, filter_expression={ "Dimensions": { "Key": "SERVICE", "Values": ["Amazon Elastic Compute Cloud - Compute", "Amazon Simple Storage Service"], "MatchOptions": ["EQUALS"] } } ) Args: ctx: MCP context baseline_date_range: The reference period for comparison (exactly one month) comparison_date_range: The comparison period (exactly one month) metric_for_comparison: Cost metric to analyze drivers for (UnblendedCost, BlendedCost, etc.) group_by: Either a dictionary with Type and Key, or simply a string key to group by filter_expression: Filter criteria as a Python dictionary Returns: with specific usage types, usage quantity changes, driver types (savings plans, discounts, usage changes, support fees), and contextual information

[DEPRECATED] Retrieve AWS cost and usage data. This tool retrieves AWS cost and usage data for AWS services during a specified billing period, with optional filtering and grouping. It dynamically generates cost reports tailored to specific needs by specifying parameters such as granularity, billing period dates, and filter criteria. Note: The end_date is treated as inclusive in this tool, meaning if you specify an end_date of "2025-01-31", the results will include data for January 31st. This differs from the AWS Cost Explorer API which treats end_date as exclusive. IMPORTANT: When using UsageQuantity metric, AWS aggregates usage numbers without considering units. This makes results meaningless when different usage types have different units (e.g., EC2 compute hours vs data transfer GB). For meaningful UsageQuantity results, you MUST be very specific with filtering, including USAGE_TYPE or USAGE_TYPE_GROUP. Example: Get monthly costs for EC2 and S3 services in us-east-1 for May 2025 await get_cost_and_usage( ctx=context, date_range={ "start_date": "2025-05-01", "end_date": "2025-05-31" }, granularity="MONTHLY", group_by={"Type": "DIMENSION", "Key": "SERVICE"}, filter_expression={ "And": [ { "Dimensions": { "Key": "SERVICE", "Values": ["Amazon Elastic Compute Cloud - Compute", "Amazon Simple Storage Service"], "MatchOptions": ["EQUALS"] } }, { "Dimensions": { "Key": "REGION", "Values": ["us-east-1"], "MatchOptions": ["EQUALS"] } } ] }, metric="UnblendedCost" ) Example: Get meaningful UsageQuantity for specific EC2 instance usage await get_cost_and_usage( ctx=context, { "date_range": { "start_date": "2025-05-01", "end_date": "2025-05-31" }, "filter_expression": { "And": [ { "Dimensions": { "Values": [ "Amazon Elastic Compute Cloud - Compute" ], "Key": "SERVICE", "MatchOptions": [ "EQUALS" ] } }, { "Dimensions": { "Values": [ "EC2: Running Hours" ], "Key": "USAGE_TYPE_GROUP", "MatchOptions": [ "EQUALS" ] } } ] }, "metric": "UsageQuantity", "group_by": "USAGE_TYPE", "granularity": "MONTHLY" } Args: ctx: MCP context date_range: The billing period start and end dates in YYYY-MM-DD format (end date is inclusive) granularity: The granularity at which cost data is aggregated (DAILY, MONTHLY, HOURLY) group_by: Either a dictionary with Type and Key, or simply a string key to group by filter_expression: Filter criteria as a Python dictionary metric: Cost metric to use (UnblendedCost, BlendedCost, etc.) Returns: Dictionary containing cost report data grouped according to the specified parameters