AWS Resources MCP Server

What does “AWS Resources” MCP Server do?

The AWS Resources MCP Server is a Python-based implementation of the Model Context Protocol (MCP) that enables AI assistants—such as Claude—to interact directly with AWS services using boto3. This server allows the execution of generated Python code for querying and managing AWS resources, offering powerful AWS operations with appropriate sandboxing and containerization. By simply passing your AWS credentials, developers and Ops teams can manage AWS resources, perform queries, and execute management tasks, all through conversational AI interfaces without complex setups. The server is flexible, supporting both read and write operations, governed entirely by the permissions of your AWS user role.

List of Prompts

No prompt templates are specified in the available repository files.

List of Resources

No explicit MCP resources are listed or described in the available repository files.

List of Tools

No explicit tool definitions (e.g., query_database, read_write_file, call_api) are listed in the available repository files.

Use Cases of this MCP Server

• AWS Resource Querying
  Use AI assistants to query information about AWS resources (e.g., EC2 instances, S3 buckets, Lambda functions) directly via natural language.
• AWS Resource Management
  Perform management operations, such as starting/stopping EC2 instances or creating/modifying resources, according to your AWS credentials.
• DevOps Automation
  Enable rapid, conversational automation of AWS infrastructure tasks without manual CLI or console work.
• Security and Compliance Checks
  Run ad-hoc code to inspect AWS resources for compliance, security group settings, or configuration drift, leveraging the full power of boto3.
• Incident Response and Troubleshooting
  Resolve incidents or troubleshoot AWS environments interactively via AI, reducing response time by running diagnostic code on demand.

How to set it up

Windsurf

1. Ensure Node.js is installed.
2. Open your Windsurf configuration file.
3. Locate the mcpServers object.
4. Add the AWS Resources MCP Server with a JSON snippet like below.
5. Save the file and restart Windsurf to apply changes.

"mcpServers": {
  "aws-resources": {
    "command": "npx",
    "args": ["@aws/mcp-server@latest"],
    "env": {
      "AWS_ACCESS_KEY_ID": "your-access-key-id",
      "AWS_SECRET_ACCESS_KEY": "your-secret-access-key"
    }
  }
}

Note: Secure your AWS credentials using environment variables as shown above.

Claude

1. Open Claude’s MCP integration settings.
2. Add a new MCP server entry.
3. Input the AWS Resources MCP Server as shown below.
4. Save and restart Claude if necessary.

"mcpServers": {
  "aws-resources": {
    "command": "npx",
    "args": ["@aws/mcp-server@latest"],
    "env": {
      "AWS_ACCESS_KEY_ID": "your-access-key-id",
      "AWS_SECRET_ACCESS_KEY": "your-secret-access-key"
    }
  }
}

Note: Use environment variables for sensitive credentials.

Cursor

1. Install Node.js if not already present.
2. Edit Cursor’s config file to include the MCP server.
3. Insert the following configuration.
4. Save your changes and restart Cursor.

"mcpServers": {
  "aws-resources": {
    "command": "npx",
    "args": ["@aws/mcp-server@latest"],
    "env": {
      "AWS_ACCESS_KEY_ID": "your-access-key-id",
      "AWS_SECRET_ACCESS_KEY": "your-secret-access-key"
    }
  }
}

Cline

1. Make sure Cline is set up with Node.js.
2. Open your configuration file.
3. Add the MCP server as shown.
4. Save and restart your environment.

"mcpServers": {
  "aws-resources": {
    "command": "npx",
    "args": ["@aws/mcp-server@latest"],
    "env": {
      "AWS_ACCESS_KEY_ID": "your-access-key-id",
      "AWS_SECRET_ACCESS_KEY": "your-secret-access-key"
    }
  }
}

Securing API Keys:
Always use environment variables to pass sensitive keys.
Example:

"env": {
  "AWS_ACCESS_KEY_ID": "your-access-key-id",
  "AWS_SECRET_ACCESS_KEY": "your-secret-access-key"
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "aws-resources": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “aws-resources” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Between the available information and the missing sections (no explicit tools, resources, or prompt templates), this MCP server achieves a basic but valuable use case for AWS automation, but would need more documentation and explicit MCP features to score higher.

Our opinion

Given the available features and documentation, this MCP server is functional and targets a clear use case (AWS automation via conversational AI), but lacks explicit MCP standard features like prompt templates, resource definitions, or tool schemas. It is straightforward for advanced users, but could benefit from more clarity on capabilities and security for wider adoption.
Score: 5/10

MCP Score