Aws Cost Explorer MCP Server

subgraph "Claude Desktop" Host --> MCPClient[MCP Client] end

Local serverstdioPython

What is the Aws Cost Explorer MCP Server?

subgraph "Claude Desktop" Host --> MCPClient[MCP Client] end

What you get

This tool provides a convenient way to analyze and visualize AWS cloud spending data using Anthropic's Claude model as an interactive interface. It functions as 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.

  • 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

Configuration and credentials

  • Python 3.12 - AWS credentials with Cost Explorer access - Anthropic API access (for Claude integration) - [Optional] Amazon Bedrock access (for LangGraph Agent) - [Optional] Amazon EC2 for running a remote MCP server

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

How to install the Aws Cost Explorer MCP Server

{
  "mcpServers": {
    "aws-cost-explorer": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "AWS_ACCESS_KEY_ID",
        "-e",
        "AWS_SECRET_ACCESS_KEY",
        "-e",
        "AWS_REGION",
        "-e",
        "BEDROCK_LOG_GROUP_NAME",
        "-e",
        "MCP_TRANSPORT",
        "-e",
        "CROSS_ACCOUNT_ROLE_NAME",
        "aws-cost-explorer-mcp:latest"
      ],
      "env": {
        "AWS_ACCESS_KEY_ID": "YOUR_AWS_ACCESS_KEY_ID",
        "AWS_SECRET_ACCESS_KEY": "YOUR_AWS_SECRET_ACCESS_KEY",
        "AWS_REGION": "us-east-1",
        "BEDROCK_LOG_GROUP_NAME": "YOUR_CLOUDWATCH_BEDROCK_MODEL_INVOCATION_LOG_GROUP_NAME",
        "CROSS_ACCOUNT_ROLE_NAME": "ROLE_NAME_FOR_THE_ROLE_TO_ASSUME_IN_OTHER_ACCOUNTS",
        "MCP_TRANSPORT": "stdio"
      }
    }
  }
}

From the project documentation. Replace placeholders and example paths before connecting.

Configuration

  • Python 3.12 - AWS credentials with Cost Explorer access - Anthropic API access (for Claude integration) - [Optional] Amazon Bedrock access (for LangGraph Agent) - [Optional] Amazon EC2 for running a remote MCP server
VariableDescriptionRequired
AWS_ACCESS_KEY_IDDeclared in the maintainer’s client configuration.Check documentation
AWS_SECRET_ACCESS_KEYDeclared in the maintainer’s client configuration.Check documentation
AWS_REGIONDeclared in the maintainer’s client configuration.Check documentation
BEDROCK_LOG_GROUP_NAMEDeclared in the maintainer’s client configuration.Check documentation
CROSS_ACCOUNT_ROLE_NAMEDeclared in the maintainer’s client configuration.Check documentation
MCP_TRANSPORTDeclared in the maintainer’s client configuration.Check documentation

Example prompts to try

  • “Use Aws Cost Explorer to Prerequisites.”

Frequently asked questions

subgraph "Claude Desktop" Host --> MCPClient[MCP Client] end Confirm the tools offered by your installed version in the connected client. Tool availability and permissions depend on the server and account configuration.