MCP сервер для Cost Explorer:

https://github.com/aarora79/aws-cost-explorer-mcp-server

Даёт доступ Claude к Cost Explorer, что позволяет запрашивать и рисовать все расходы с помощью обычных текстовых запросов. Опционально также есть возможность подключения расходов на Bedrock.

По умолчанию работает локально, но можно запустить и в качестве виртуалки на AWS, чтобы использовать роль для доступа.

#MCP #cost_optimization

MCP server for Terraform:

https://github.com/nwiizo/tfmcp

◽️ Reading Terraform configuration files
◽️ Analyzing Terraform plan outputs
◽️ Applying Terraform configurations
◽️ Managing Terraform state
◽️ Creating and modifying Terraform configurations

#MCP #Terraform

MCP-server for Kubernetes:

https://github.com/Flux159/mcp-server-kubernetes

▫️ Connect to a Kubernetes cluster
▫️ List all pods
▫️ List all services
▫️ List all deployments
▫️ List all nodes
▫️ Create a pod
▫️ Delete a pod
▫️ Describe a pod
▫️ List all namespaces
▫️ Get logs from a pod for debugging (supports pods deployments jobs and label selectors)
▫️ Support Helm v3 for installing charts
▪️ Install charts with custom values
▪️ Uninstall releases
▪️ Upgrade existing releases
▪️ Support for namespaces
▪️ Support for version specification
▪️ Support for custom repositories

#MCP #Kubernetes

MCP with Bedrock:

- Allows AI models to access information outside their built-in knowledge.
- Help build tools that enable AI models to perform actions (such as visiting websites or checking the weather).
- Establish communication through a standardized protocol between the user, the AI model and external tools.

https://community.aws/content/2uFvyCPQt7KcMxD9ldsJyjZM1Wp/model-context-protocol-mcp-and-amazon-bedrock

For example, if you ask "get me a summary of the blog post at this URL", the system will:

- Process your request
- Recognize it needs to use a tool to visit the webpage
- Fetch the content from the URL
- Return the information to the model
- Generate a summary based on the fetched content

#MCP #Bedrock

Q Developer CLI + MCP

https://aws.amazon.com/blogs/devops/extend-the-amazon-q-developer-cli-with-mcp/

Full list of AWS MCP Servers:

https://github.com/awslabs/mcp

#Q #MCP

Официальный MCP-server для EKS:

https://aws.amazon.com/blogs/containers/accelerating-application-development-with-the-amazon-eks-model-context-protocol-server/

#EKS #MCP

Официальный MCP-server для ECS:

https://aws.amazon.com/blogs/containers/automating-ai-assisted-container-deployments-with-amazon-ecs-mcp-server/

#ECS #MCP

Полный список доступных MCP серверов от AWS:

https://awslabs.github.io/mcp/

• Core MCP Server
• Amazon Bedrock Knowledge Base Retrieval MCP Server
• AWS CDK MCP Server
• Cost Analysis MCP Server
• Amazon Nova Canvas MCP Server
• AWS Documentation MCP Server
• AWS Lambda Tool MCP Server 👍
• AWS Diagram MCP Server
• AWS Step Functions Tool MCP Server
• AWS Terraform MCP Server 🔥
• Git Repo Research MCP Server
• CloudFormation MCP Server
• AWS Serverless MCP Server 💪
• Finch MCP Server
• Amazon EKS MCP Server 🔥
• Amazon ECS MCP Server 🔥
• AWS Support MCP Server

#MCP

Теперь работать с AWS можно прямо из ChatGPT. 😃

Доступно для Pro/Plus подписки — нужно включить в настройках Connectors -> Advanced settings -> Developer mode и добавить нужный MCP.

Официальный публичный MCP-сервер AWS документации:

{
  "name": "AWS Knowledge MCP Server",
  "url": "https://knowledge-mcp.global.api.aws",
  "authentication": "None"
}

#MCP