AWS Cost Explorer and Amazon Bedrock Model Invocation Logs MCP Server logo

AWS Cost Explorer and Amazon Bedrock Model Invocation Logs MCP Server

by aarora79

This MCP server provides a way to access AWS spend data via Cost Explorer and Amazon Bedrock usage data via Model invocation logs in Amazon Cloud Watch through Anthropic's MCP. It allows users to analyze and visualize AWS cloud spending data using Anthropic's Claude model as an interactive interface.

View on GitHub

Last updated: N/A

What is AWS Cost Explorer and Amazon Bedrock Model Invocation Logs MCP Server?

This tool is an MCP server that exposes AWS Cost Explorer API functionality to Claude Desktop, allowing you to ask questions about your AWS spend in natural language. It also provides access to Amazon Bedrock usage data via Model Invocation Logs in CloudWatch.

How to use AWS Cost Explorer and Amazon Bedrock Model Invocation Logs MCP Server?

To use this server, you need to install the required dependencies, configure your AWS credentials, and set up the MCP server either locally or remotely. You can then configure Claude Desktop to connect to the server and query your cost data through natural language. You can also use it with a LangGraph Agent.

Key features of AWS Cost Explorer and Amazon Bedrock Model Invocation Logs MCP Server

  • Amazon EC2 Spend Analysis

  • Amazon Bedrock Spend Analysis

  • Service Spend Reports

  • Detailed Cost Breakdown

  • Interactive Interface

Use cases of AWS Cost Explorer and Amazon Bedrock Model Invocation Logs MCP Server

  • Analyzing EC2 spending for the last day

  • Viewing breakdown of Bedrock spend by region, users, and models over the last 30 days

  • Analyzing spending across all AWS services for the last 30 days

  • Getting granular cost data by day, region, service, and instance type

FAQ from AWS Cost Explorer and Amazon Bedrock Model Invocation Logs MCP Server

How do I configure AWS credentials?

You need to set up your credentials in ~/.aws/credentials and ~/.aws/config. If you use AWS IAM Identity Center, follow the documentation to configure your short-term credentials.

How do I install the dependencies?

Use uv to create a virtual environment and install the dependencies from the pyproject.toml file.

How do I run the server locally?

Set the MCP_TRANSPORT environment variable to stdio and run the server.py script.

How do I configure Claude Desktop to use this server?

Add the server configuration to your Claude Desktop configuration file, specifying the command and arguments to run the server.

How do I run the server remotely?

Set the MCP_TRANSPORT environment variable to sse and run the server.py script on an EC2 instance. Configure the security group to allow access to TCP port 8000.