AWS / Community
AWS MCP Server
Open source MCP servers from AWS Labs that give AI coding agents access to AWS documentation, best practices, and contextual guidance for building on AWS.
Last reviewed Feb 28, 2026
What it does
AWS provides open source MCP servers that connect AI coding agents to AWS documentation, contextual guidance, and best practices. These servers improve output quality by giving agents access to the latest AWS docs, workflow automation, and specialized domain knowledge. Individual servers (e.g., Powertools, Lambda) expose different tool sets.
Available tools
Tool availability depends on which AWS MCP server you use. Common patterns:
| Server type | Example tools | What it does |
|---|---|---|
| Documentation | search_docs, get_guidance |
Search AWS docs and retrieve guidance |
| Powertools | powertools_* |
Access Powertools for AWS Lambda docs and patterns |
| Lambda runners | run_mcp_server |
Run MCP servers in AWS Lambda |
See AWS MCP documentation for the full catalog and tool listings.
Setup by tool
Cursor (Powertools example)
Create .cursor/mcp.json:
{
"mcpServers": {
"aws-powertools": {
"command": "npx",
"args": ["-y", "powertools-for-aws-mcp"]
}
}
}
Other AWS MCP packages may require different commands and env vars. Check each server's README.
Claude Code
Add the same configuration. Documentation-focused servers often require no API keys. Servers that interact with AWS resources need appropriate credentials (e.g., AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY or IAM roles).
VS Code / GitHub Copilot
Configure the desired AWS MCP server in your client. For Lambda-based deployment, see AWS guidance on running MCP servers in Lambda with OAuth and WAF.
When to use this
- AWS development: Agents reference current AWS docs and best practices
- Lambda development: Use Powertools MCP for tracing, logging, and validation patterns
- Architecture guidance: Get contextual recommendations for service selection and design
- Workflow automation: Integrate AWS guidance into agent-driven development loops
Security considerations
- Documentation servers typically do not need AWS credentials
- Servers that call AWS APIs require credentials; use IAM roles with least privilege
- For Lambda deployment, follow AWS guidance on OAuth, WAF, and multi-AZ setup
- Do not grant broad AWS permissions to MCP servers used by agents
- Audit which servers are enabled and what access they have
Compatibility
Related MCP servers
Docker MCP Server
Docker MCP Gateway orchestrates MCP servers in isolated containers, providing secure discovery and execution of Model Context Protocol servers across AI coding tools.
Figma MCP Server
Official Figma MCP server that brings design context, variables, components, and Code Connect data into AI coding sessions for design-to-code workflows.
Firebase MCP Server
Experimental Firebase MCP server that gives AI coding agents access to Firestore, Auth, security rules, Cloud Messaging, and project management through the Firebase CLI.