A

Aws Cost Explorer MCP Server

A tool for querying AWS cost data and Bedrock usage logs via the MCP protocol
3 points
631

What is the AWS Cost Explorer MCP Server?

The AWS Cost Explorer MCP Server is a tool based on the Anthropic Model Context Protocol (MCP) that allows you to query your AWS cloud spending and model usage via natural language. You can easily understand the costs of EC2 instances, Bedrock model calls, and other AWS services.

How to use the AWS Cost Explorer MCP Server?

By configuring the MCP client or proxy server, you can connect to the MCP server and start querying your AWS cost data.

Applicable Scenarios

This tool is suitable for enterprise users who need to regularly analyze AWS costs, especially those who want to gain in - depth insights into the costs of their EC2 instances and Bedrock model calls.

Main Features

Get the past day's EC2 spendingView the detailed spending of EC2 instances in the past day.
Break down detailed costs by dayBreak down costs in detail according to date, region, service, and instance type.
Get daily Bedrock usage statisticsStatistically analyze the regional and user usage of Bedrock model calls by day.
Get hourly Bedrock usage statisticsStatistically analyze the regional and user usage of Bedrock model calls by day and hour.

Advantages and Limitations

Advantages
Query AWS cost data via natural language, simple and easy to use.
Support cross - account query of AWS costs.
Visually display AWS costs for easy decision - making.
Quick to get started without programming.
Limitations
Require AWS credentials and permission settings.
Some advanced features may require additional configuration.
Only support the HTTPS protocol and cannot run directly locally.

How to Use

Install Dependencies
Ensure that Python 3.12 and necessary dependencies are installed.
Configure Environment Variables
Set AWS credentials and other necessary parameters.
Start the MCP Server
Start the MCP server using a Python script.

Usage Examples

Query the EC2 costs in the past weekGet the total cost and detailed breakdown of EC2 instances in the past week.
Analyze Bedrock model call costsView the cost distribution of Bedrock model calls in the past month.

Frequently Asked Questions

How to configure AWS credentials?
Does it support cross - account query?
How to deploy to the production environment?

Related Resources

GitHub Repository
Project source code and documentation.
AWS Cost Explorer API Documentation
Learn more about the AWS Cost Explorer API.
Anthropic MCP Official Documentation
Understand how the MCP protocol works.
Installation
Copy the following command to your Client for configuration
{
  "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_ACCESS_KEY_ID",
        "AWS_SECRET_ACCESS_KEY": "YOUR_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"
      }
    }
  }
}

{
  "mcpServers": {
    "aws_cost_explorer": {
      "command": "uv",
      "args": [
          "--directory",
          "/path/to/aws-cost-explorer-mcp-server",
          "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_MODEL_INVOCATION_LOG_GROUP_NAME",
        "CROSS_ACCOUNT_ROLE_NAME": "ROLE_NAME_FOR_THE_ROLE_TO_ASSUME_IN_OTHER_ACCOUNTS",
        "MCP_TRANSPORT": "stdio"
      }
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.
E
Edgeone Pages MCP Server
EdgeOne Pages MCP is a service that quickly deploys HTML content to EdgeOne Pages via the MCP protocol and obtains a public URL
TypeScript
250
4.8 points
K
Kubernetes
An MCP server based on Kubernetes for managing and operating Kubernetes clusters
TypeScript
544
5 points
A
Awslabs Cost Analysis MCP Server
The AWS MCP Servers are a set of dedicated servers based on the Model Context Protocol, offering various AWS-related functions, including document retrieval, knowledge base query, CDK best practices, cost analysis, image generation, etc., aiming to enhance the integration of AI applications with AWS services through a standardized protocol.
Python
2.6K
5 points
2
2344
Opik is an open-source LLM evaluation framework that supports tracking, evaluating, and monitoring LLM applications, helping developers build more efficient and cost-effective LLM systems.
TypeScript
7.1K
5 points
M
MCP K8s Go
An MCP server based on Golang for connecting to Kubernetes clusters, providing resource query and operation functions.
Go
308
4 points
S
Solon
Solon is an efficient, open, and eco - friendly Java enterprise application development framework that supports all - scenario development. It features high performance, low memory consumption, fast startup, and small - volume packaging. It is compatible with Java 8 to Java 24 and the GraalVM native runtime.
Java
2.5K
5 points
K
Kubectl MCP Server
The Kubectl MCP Tool is a Kubernetes interaction tool based on the Model Context Protocol (MCP), allowing AI assistants to interact with Kubernetes clusters using natural language.
Python
419
4.5 points
K
Kubernetes Manager
A Kubernetes cluster management server based on the MCP protocol, supporting interaction with the Kubernetes cluster through the command line or chat interface, providing functions such as resource management and Helm chart operations.
TypeScript
559
5 points
Featured MCP Services
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
1.7K
5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
823
4.3 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
79
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
130
4.5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
554
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
6.6K
4.5 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
5.2K
4.7 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
745
4.8 points
AIbase
Zhiqi Future, Your AI Solution Think Tank
© 2025AIbase