aws
MCP (Model context protocol) server to connect MCP client such as Claude Desktop.
claude mcp add --transport stdio codewithdpk-aws-mcp-server node /ABSOLUTE/PATH/TO/PARENT/FOLDER/aws-mcp-server/build/index.js \ --env AWS_ACCESS_KEY_ID="your_access_key_id" \ --env AWS_ACCESS_SECRET_KEY="your_secret_access_key"
How to use
This MCP server provides access to AWS EC2 instance data. It exposes a tool named get-aws-instances that retrieves a list of running EC2 instances for a specified AWS region, including details such as Instance ID, instance type, public and private IPs, and current state. The server is implemented in Node.js and builds to a JavaScript runtime, allowing clients using the MCP protocol to query for instance information in a structured way. To use it, connect to the server via an MCP client and invoke the get-aws-instances tool with a region string (for example, ap-south-1). The server will return a list of instances in that region along with their metadata, and it supports multiple availability zones within the region.
Example tool usage:
server.tool("get-aws-instances", { region: "ap-south-1" })
How to install
Prerequisites:
- Node.js 18 or later
- npm (comes with Node.js)
- AWS account with IAM credentials that have EC2 read permissions
Step-by-step installation:
-
Clone the repository and navigate into it: git clone https://github.com/codewithdpk/aws-mcp-server.git cd aws-mcp-server
-
Install dependencies: npm install
-
Configure AWS credentials: Create a .env file in the project root with:
AWS_ACCESS_KEY_ID=your_access_key_id AWS_ACCESS_SECRET_KEY=your_secret_access_key
-
Build the server: npm run build
-
Run the server locally (example): node build/index.js
-
If you need to run via MCP tooling, ensure the mcp_config references the built entry point and environment variables are provided as needed.
Additional notes
Tips and common issues:
- Ensure AWS credentials have at least EC2 read permissions to list instances.
- If the server cannot access AWS, verify that AWS_REGION or the region parameter is correctly specified when calling the tool.
- When deploying, consider using a dedicated IAM role or user with restricted permissions for security.
- The server relies on the AWS SDK; ensure network access to AWS services from your host or deployment environment.
- For Claude Desktop integration (if used), configure the mcpServers entry in claude_desktop_config.json to point to the built index.js as described in the README. Ensure you supply valid absolute paths.
- If you modify code, rebuild with npm run build to generate updated artifacts.
Related MCP Servers
MCP-Bridge
A middleware to provide an openAI compatible endpoint that can call MCP tools
mcp_server_filesystem
MCP File System Server: A secure Model Context Protocol server that provides file operations for AI assistants. Enables Claude and other assistants to safely read, write, and list files in a designated project directory with robust path validation and security controls.
Excel -Master
Excel MCP Server - Manipulate Excel files without Microsoft Excel. Model Context Protocol for XLSX, XLSM with Claude AI integration
mcp-chat-widget
Configure, host and embed MCP-enabled chat widgets for your website or product. Lightweight and extensible Chatbase clone to remotely configure and embed your agents anywhere.
agi -agent
A modular AGI agent framework based on MCP (Multi-Context Processing), inspired by Manus, with ChatGPT-style LLM integration and task control.
llm-bridge
A model-agnostic Message Control Protocol (MCP) server that enables seamless integration with various Large Language Models (LLMs) like GPT, DeepSeek, Claude, and more.