aws-cost-explorer-mcp-server
This project is an MCP server client system tailored to analyze AWS spending data and enable natural language querying through Anthropic's Claude. It supports local and remote operation, offering detailed insights into AWS spending patterns.
What AWS services does this tool support?
The tool supports AWS Cost Explorer and Amazon Bedrock Model Invocation Logs, providing detailed spending analysis for EC2 and other AWS services.
Can I use this tool to analyze spending from multiple AWS accounts?
Yes, the tool can access AWS spend information from other accounts as long as the IAM role used by the MCP server can assume roles in those accounts.
Is it possible to run the MCP server remotely?
Yes, you can run the MCP server on an Amazon EC2 instance and access it via a remote MCP client.
How do I secure the remote MCP server?
You can use nginx as a reverse-proxy to provide an HTTPS endpoint for connecting to the MCP server, ensuring secure communication.
What are the prerequisites for using this tool?
You need Python 3.12, AWS credentials with Cost Explorer access, Anthropic API access, and optionally Amazon Bedrock access for LangGraph Agent.