SSyncDev

A Sample For Understanding Cloud Spend MCP Server

MCP for AWS Cost Explorer and CloudWatch logs

Local serverstdioPython

What is the A Sample For Understanding Cloud Spend MCP Server?

MCP for AWS Cost Explorer and CloudWatch logs

What it actually does

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

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

  • 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 A Sample For Understanding Cloud Spend MCP Server

{
  "mcpServers": {
    "aws-cost-explorer": {
      "command": "docker",
      "args": [ "run", "-i", "--rm", "-e", "AWS_PROFILE", "-e", "AWS_REGION", "-e", "BEDROCK_LOG_GROUP_NAME", "-e", "MCP_TRANSPORT", "aws-cost-explorer-mcp:latest" ],
      "env": {
        "AWS_PROFILE": "YOUR_AWS_PROFILE_NAME",
        "AWS_REGION": "us-east-1",
        "BEDROCK_LOG_GROUP_NAME": "YOUR_CLOUDWATCH_BEDROCK_MODEL_INVOCATION_LOG_GROUP_NAME",
        "MCP_TRANSPORT": "stdio"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

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_PROFILEConfiguration value read at startup.Optional
AWS_REGIONConfiguration value read at startup.Optional
BEDROCK_LOG_GROUP_NAMEConfiguration value read at startup.Optional
MCP_TRANSPORTConfiguration value read at startup.Optional
MCP_SERVER_URLEndpoint or connection string the server talks to.Yes
MCP_SERVER_PORTConfiguration value read at startup.Optional

Example prompts to try

  • “Use A Sample For Understanding Cloud Spend to Prerequisites.”

Frequently asked questions

Python 3.12, AWS credentials with Cost Explorer access, and Anthropic API access. Optionally, Amazon Bedrock access (for LangGraph Agent) and an EC2 instance for remote deployment.

Alternatives to the A Sample For Understanding Cloud Spend MCP Server

n8n

Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.

Developer ToolsRemoteTypeScript★ 22.5k

AWS

Official

AWS Labs' official server suite — current AWS docs, CDK guidance, cost analysis and service tools.

Cloud & DevOpsPython★ 7.0k

Keel

Network diagnostics — ping, traceroute, DNS, port scanning, and connectivity testing.

Cloud & DevOps

Synlake

Unified API to query AWS, GCP, Azure and generate Terraform/CLI execution kits for AI agents.

Cloud & DevOpsRemote

Zammad

Stateless remote MCP server for Zammad — full ticket operations, an intelligent search layer and OAuth 2.1, running on Node.js or Cloudflare Workers

Cloud & DevOpsTypeScript

Glyph

Glyph guards your MCP infrastructure through two complementary approaches:

Cloud & DevOps