aws-cost-explorer-mcp-server
If you are the rightful owner of aws-cost-explorer-mcp-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
An MCP server for accessing AWS spend data via Cost Explorer and Amazon Bedrock usage data through Model Invocation Logs in Amazon CloudWatch.
The AWS Cost Explorer and Amazon Bedrock Model Invocation Logs MCP Server & Client is a tool designed to facilitate the analysis and visualization of AWS cloud spending data. It leverages Anthropic's Claude model as an interactive interface, functioning as an MCP server that exposes AWS Cost Explorer API functionality to Claude Desktop. This allows users to query their AWS spend in natural language, providing a user-friendly way to understand and manage cloud expenses. The server can be run locally or remotely on Amazon EC2, and it supports cross-account access if the IAM role used by the server can assume roles in other accounts. The tool is particularly useful for organizations looking to gain insights into their AWS spending patterns, optimize costs, and make informed decisions based on detailed financial data.
Features
- Amazon EC2 Spend Analysis: View detailed breakdowns of EC2 spending for the last day.
- Amazon Bedrock Spend Analysis: View breakdown by region, users, and models over the last 30 days.
- Service Spend Reports: Analyze spending across all AWS services for the last 30 days.
- Detailed Cost Breakdown: Get granular cost data by day, region, service, and instance type.
- Interactive Interface: Use Claude to query your cost data through natural language.
Tools
get_ec2_spend_last_day
Retrieves EC2 spending data for the previous day.
get_detailed_breakdown_by_day
Delivers a comprehensive analysis of costs by region, service, and instance type.
get_bedrock_daily_usage_stats
Delivers a per-day breakdown of model usage by region and users.
get_bedrock_hourly_usage_stats
Delivers a per-day per-hour breakdown of model usage by region and users.
