Skill

Build and deploy AWS infrastructure with CDK best practices

Configuration guide for AWS MCP servers enabling documentation search and API access via uvx or HTTP endpoints.

Works with awscdklambdas3cloudwatch

35
Spark score
out of 100
Updated 2 days ago
Version 15.16.0
Models
universal

Add to Favorites

Why it matters

Accelerate AWS cloud development by providing specialized skills for infrastructure-as-code, serverless architecture, cost optimization, and AI agent deployment with integrated MCP servers that query live AWS documentation and services.

Outcomes

What it gets done

01

Generate CDK stacks with Lambda functions, API Gateway, and proper IAM permissions following AWS best practices

02

Estimate and analyze AWS costs across services using integrated pricing and cost explorer tools

03

Configure CloudWatch monitoring, alarms, and observability for serverless applications

04

Deploy and manage AI agents with Bedrock AgentCore including memory, identity, and runtime services

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/ag-aws-mcp-setup | bash

Overview

AWS MCP Server Configuration Guide

Configuration guide covering two AWS MCP deployment options with setup instructions, credential configuration, and verification steps. Use when configuring AWS MCP servers, setting up AWS documentation tools, or troubleshooting MCP connectivity. Covers aws-mcp, awsdocs, uvx setup, and MCP server configuration tasks.

What it does

This guide helps configure AWS MCP tools for AI agents. Two options are available: Full AWS MCP Server (requires Python 3.10+, uvx, AWS credentials) for executing AWS API calls plus documentation search, or AWS Documentation MCP (no requirements) for documentation search only.

When to use - and when NOT to

Use this skill when you need to configure AWS MCP servers for documentation search and API access. Use when setting up AWS MCP, configuring AWS documentation tools, troubleshooting MCP connectivity, or when user mentions aws-mcp, awsdocs, uvx setup, or MCP server configuration.

Do NOT use this skill only when the task clearly matches its upstream source and local project context. Verify commands, generated code, dependencies, credentials, and external service behavior before applying changes. Do not treat examples as a substitute for environment-specific tests, security review, or user approval for destructive or costly actions.

Inputs and outputs

Before configuring, check if AWS MCP tools are already available. Look for tool name patterns: mcp__aws-mcp__* or mcp__aws__* indicates Full AWS MCP Server configured; mcp__*awsdocs*__aws___* indicates AWS Documentation MCP configured.

Agent tools use hierarchical configuration with precedence: local → project → user → enterprise. Configuration files include .claude.json (local/user scope) and .mcp.json (project scope).

Check existing configuration:

# Check project config
cat .mcp.json 2>/dev/null | grep -E '"(aws-mcp|aws|awsdocs)"'

# Check user config
cat ~/.claude.json 2>/dev/null | grep -E '"(aws-mcp|aws|awsdocs)"'

# Or use Claude CLI
claude mcp list

For Full AWS MCP Server configuration:

{
  "mcpServers": {
    "aws-mcp": {
      "command": "uvx",
      "args": [
        "mcp-proxy-for-aws@latest",
        "https://aws-mcp.us-east-1.api.aws/mcp",
        "--metadata", "AWS_REGION=us-west-2"
      ]
    }
  }
}

For AWS Documentation MCP Server configuration:

{
  "mcpServers": {
    "awsdocs": {
      "type": "http",
      "url": "https://knowledge-mcp.global.api.aws"
    }
  }
}

Required IAM permissions for Full AWS MCP Server:

{
  "Version": "2012-10-17",
  "Statement": [{
    "Effect": "Allow",
    "Action": [
      "aws-mcp:InvokeMCP",
      "aws-mcp:CallReadOnlyTool",
      "aws-mcp:CallReadWriteTool"
    ],
    "Resource": "*"
  }]
}

Credential configuration options include AWS Profile (recommended for development), environment variables, or IAM Role (for EC2/ECS/Lambda).

Integrations

Full AWS MCP Server requires Python 3.10+ with uv package manager and AWS credentials configured via profile, environment variables, or IAM role. Reference: https://github.com/aws/mcp-proxy-for-aws

AWS Documentation MCP Server requires no authentication or local dependencies and uses HTTP endpoint at https://knowledge-mcp.global.api.aws

Configuration files supported: .claude.json (local project or user home directory), .mcp.json (project root), and system managed directories (enterprise scope).

Who it's for

For users who need to configure AWS MCP servers with either full API execution capabilities (requiring Python 3.10+, uvx, and AWS credentials) or documentation search only (no requirements).

FAQ

Common questions

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.