AWS Labs MCP
Comprehensive AWS services integration suite
What is AWS Labs MCP?
AWS Labs MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to aws labs mcp provides a comprehensive suite of mcp servers for aws services including bedrock, cdk, cost analysis, and infrastructure management. built with fastmcp for enterprise-grade aws integratio...
AWS Labs MCP provides a comprehensive suite of MCP servers for AWS services including Bedrock, CDK, cost analysis, and infrastructure management. Built with FastMCP for enterprise-grade AWS integration.
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Bedrock Knowledge Base retrieval
- CDK best practices and deployment
- Cost analysis and optimization
- CloudFormation management
- Nova Canvas image generation
- Comprehensive AWS documentation access
Use Cases
Maintainer
Works with
Installation
PIP
pip install mcp-server-awsManual Installation
uvx mcp-server-awsConfiguration
Configuration Details
.aws/credentials
Security
Authentication
Performance
Response Metrics
Resource Usage
How to Set Up and Use AWS Labs MCP
The AWS Labs MCP suite is a collection of open-source MCP servers maintained by Amazon Web Services that connect AI coding assistants to AWS services including Bedrock Knowledge Bases, CDK and CloudFormation infrastructure management, CloudWatch observability, DynamoDB, RDS databases, EKS, Lambda, and many more. Each server is independently installable via uvx and uses your existing AWS credentials, making it easy to add specific AWS capabilities to tools like Claude Desktop, Cursor, or VS Code without writing custom integrations. Teams building on AWS use these servers to let AI assistants query infrastructure state, retrieve knowledge base content, analyze costs, and generate deployment code grounded in real account data.
Prerequisites
- Python 3.10+ and uv package manager installed
- AWS account with appropriate IAM permissions for the services you want to use
- AWS CLI configured with credentials (aws configure) or an AWS profile set up
- An MCP client such as Claude Desktop, Cursor, or VS Code with MCP support
- For Bedrock servers: Amazon Bedrock enabled in your AWS region with at least one knowledge base or model access granted
Install uv package manager
All AWS Labs MCP servers are distributed via uvx (part of uv). Install uv if you do not already have it.
curl -LsSf https://astral.sh/uv/install.sh | shConfigure AWS credentials
Ensure your AWS credentials are configured. The servers use your default profile or the profile specified in AWS_PROFILE.
aws configure
# Or set environment variables
export AWS_PROFILE=your-profile-name
export AWS_REGION=us-east-1Test a server directly
Verify a server works by running it directly with uvx before adding it to your MCP client config. The Bedrock KB retrieval server is a good starting point.
uvx awslabs.bedrock-kb-retrieval-mcp-server@latestAdd the server to your MCP client config
Open your claude_desktop_config.json and add an entry for the AWS Labs server you want to use.
Restart your MCP client
After saving the config, restart Claude Desktop or your MCP client to load the new server. Verify the AWS tools appear in the available tools list.
AWS Labs MCP Examples
Client configuration for Bedrock Knowledge Base retrieval
Configure the Bedrock KB retrieval MCP server in Claude Desktop using your AWS credentials.
{
"mcpServers": {
"awslabs.bedrock-kb-retrieval-mcp-server": {
"command": "uvx",
"args": ["awslabs.bedrock-kb-retrieval-mcp-server@latest"],
"env": {
"AWS_PROFILE": "your-profile-name",
"AWS_REGION": "us-east-1",
"FASTMCP_LOG_LEVEL": "ERROR",
"KB_INCLUSION_TAG_KEY": "mcp-enabled",
"BEDROCK_KB_RERANKING_ENABLED": "false"
}
}
}
}Prompts to try
Example prompts for AWS Labs MCP servers across different service areas.
- "Search my Bedrock knowledge bases for documentation about our authentication service"
- "What is the estimated monthly cost for running 3 t3.medium EC2 instances in us-east-1?"
- "Generate a CDK stack for an API Gateway backed by a Lambda function with DynamoDB storage"
- "Show me the CloudWatch error logs for my Lambda function in the last 1 hour"
- "List all my DynamoDB tables and suggest an optimal partition key strategy for my user data"Troubleshooting AWS Labs MCP
Server fails with 'NoCredentialsError' or 'AccessDenied'
Run 'aws sts get-caller-identity' to verify your credentials are valid. Ensure the IAM role or user has the required permissions for the specific service (e.g., bedrock:RetrieveAndGenerate for Bedrock KB).
uvx command not found when starting the server
Install uv with 'curl -LsSf https://astral.sh/uv/install.sh | sh' and ensure ~/.cargo/bin or ~/.local/bin is in your PATH. Restart your terminal after installation.
Bedrock Knowledge Base queries return no results
Verify the knowledge base is synced and active in the AWS Bedrock console. If using KB_INCLUSION_TAG_KEY, ensure your knowledge base has that tag applied in AWS. Try removing the tag filter first to confirm connectivity.
Frequently Asked Questions about AWS Labs MCP
What is AWS Labs MCP?
AWS Labs MCP is a Model Context Protocol (MCP) server that comprehensive aws services integration suite It connects AI assistants to external tools and data sources through a standardized interface.
How do I install AWS Labs MCP?
Install via pip with: pip install mcp-server-aws. Then configure your AI client to connect to this MCP server.
Which AI clients work with AWS Labs MCP?
AWS Labs MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is AWS Labs MCP free to use?
Yes, AWS Labs MCP is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
AWS Labs MCP Alternatives — Similar Cloud Services Servers
Looking for alternatives to AWS Labs MCP? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up AWS Labs MCP in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use AWS Labs MCP?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.