aws-cost-explorer-mcp-server

Overview

This MCP server enables users to query and analyze AWS spending data through natural language interfaces. It connects to AWS Cost Explorer API and CloudWatch Logs for Bedrock model invocation data. The server supports both local (stdio) and remote (SSE) deployments, with detailed configuration instructions for Claude Desktop integration and an optional Chainlit web interface. It also provides functionality for accessing cross-account AWS spending data when properly configured.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

• get_ec2_spend_last_dayget_ec2_spend_last_day()

  Retrieves EC2 spending data for the previous day

  Try:What was my EC2 spend yesterday?Try:Show me my EC2 costs from the last day
• get_detailed_breakdown_by_dayget_detailed_breakdown_by_day(days=7)

  Delivers a comprehensive analysis of costs by region, service, and instance type

  Try:Show me my AWS costs broken down by day for the last weekTry:Analyze my spending by region and service for the past 7 days
• get_bedrock_daily_usage_statsget_bedrock_daily_usage_stats(days=7, region='us-east-1', log_group_name='BedrockModelInvocationLogGroup')

  Delivers a per-day breakdown of model usage by region and users

  Try:What was my Bedrock usage like in the last week?Try:Show me daily Bedrock usage stats for us-west-2 region
• get_bedrock_hourly_usage_statsget_bedrock_hourly_usage_stats(days=7, region='us-east-1', log_group_name='BedrockModelInvocationLogGroup')

  Delivers a per-day per-hour breakdown of model usage by region and users

  Try:Show me hourly Bedrock usage patterns for the last 7 daysTry:What were my peak usage hours for Bedrock last week?

Comparable tools

Installation

# On macOS and Linux
curl -LsSf https://astral.sh/uv/install.sh | sh

# On Windows
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

git clone https://github.com/aarora79/aws-cost-explorer-mcp.git
cd aws-cost-explorer-mcp
uv venv --python 3.12 && source .venv/bin/activate && uv pip install --requirement pyproject.toml

{
  "mcpServers": {
    "aws-cost-explorer": {
      "command": "uv",
      "args": [
          "--directory",
          "/path/to/aws-cost-explorer-mcp",
          "run",
          "server.py"
      ],
      "env": {
        "AWS_ACCESS_KEY_ID": "YOUR_ACCESS_KEY_ID",
        "AWS_SECRET_ACCESS_KEY": "YOUR_SECRET_ACCESS_KEY",
        "AWS_REGION": "us-east-1",
        "BEDROCK_LOG_GROUP_NAME": "YOUR_CLOUDWATCH_BEDROCK_LOG_GROUP_NAME",
        "MCP_TRANSPORT": "stdio"
      }
    }
  }
}

FAQ

Can this MCP server access AWS spending data from other accounts?

Yes, you can set the CROSS_ACCOUNT_ROLE_NAME parameter when starting the server to assume roles in other AWS accounts.

What tools does the server expose?

The server provides tools for EC2 spending analysis, Bedrock usage statistics, and detailed cost breakdowns by day, region, service, and instance type.

Compare aws-cost-explorer-mcp-server with