AWS Cloud Development Kit MCP server

The AWS CDK MCP Server is a specialized tool that helps developers implement AWS Cloud Development Kit (CDK) best practices, provides infrastructure as code patterns, and ensures security compliance through CDK Nag integration. It offers guidance on using AWS Solutions Constructs, GenAI CDK libraries, and implementing security automation.

Installation Guide

Prerequisites

1. Install uv from Astral or the GitHub README
2. Install Python using uv python install 3.10
3. Install AWS CDK CLI using npm install -g aws-cdk

Server Setup

To install the MCP server, you have two options:

Option 1: Using uvx

Configure the MCP server in your MCP client configuration. For Amazon Q Developer CLI, edit ~/.aws/amazonq/mcp.json:

{
  "mcpServers": {
    "awslabs.cdk-mcp-server": {
      "command": "uvx",
      "args": ["awslabs.cdk-mcp-server@latest"],
      "env": {
        "FASTMCP_LOG_LEVEL": "ERROR"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

Option 2: Using Docker

First, build the Docker image:

docker build -t awslabs/cdk-mcp-server .

Then configure your MCP client configuration:

{
  "mcpServers": {
    "awslabs.cdk-mcp-server": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "--interactive",
        "--env",
        "FASTMCP_LOG_LEVEL=ERROR",
        "awslabs/cdk-mcp-server:latest"
      ],
      "env": {},
      "disabled": false,
      "autoApprove": []
    }
  }
}

Using the MCP Server

Available Tools

The MCP server provides several tools for CDK development:

• CDKGeneralGuidance: Get prescriptive advice for building AWS applications with CDK
• GetAwsSolutionsConstructPattern: Find vetted architecture patterns combining AWS services
• SearchGenAICDKConstructs: Discover GenAI CDK constructs by name or features
• GenerateBedrockAgentSchema: Create OpenAPI schemas for Bedrock Agent action groups
• LambdaLayerDocumentationProvider: Access documentation for Lambda layers implementation
• ExplainCDKNagRule: Get detailed guidance on CDK Nag security rules
• CheckCDKNagSuppressions: Validate CDK Nag suppressions in your code

Working with CDK Nag

When you run cdk synth and receive CDK Nag warnings:

1. Use the ExplainCDKNagRule tool to understand the security issue
2. Fix the issue or add suppressions with proper justification
3. Use CheckCDKNagSuppressions to validate your suppressions

Implementing CDK Workflow

The recommended workflow follows these steps:

1. Start with CDKGeneralGuidance to get best practices

2. Initialize your CDK app with cdk init app

3. Choose your implementation approach:

   • For common patterns: Use GetAwsSolutionsConstructPattern
   • For GenAI features: Use SearchGenAICDKConstructs
   • For custom needs: Write custom CDK code

4. If using Lambda functions with layers, use LambdaLayerDocumentationProvider

5. Run cdk synth to check for CDK Nag warnings

6. Address warnings with ExplainCDKNagRule

7. Run cdk deploy after resolving all issues

Amazon Bedrock Agent Schema Generation

If you're creating Bedrock Agents with Action Groups:

1. Create a Lambda function with BedrockAgentResolver from AWS Lambda Powertools
2. Use GenerateBedrockAgentSchema to create the OpenAPI specification
3. If schema generation succeeds, an openapi.json file will be created
4. If there are import errors, the tool will generate a fallback script
5. Install any missing dependencies and run the script manually: python generate_schema.py
6. Use the generated schema in your Agent CDK code with bedrock.ApiSchema.fromLocalAsset()

Security Considerations

When using this MCP server:

• Review all CDK Nag warnings and errors manually
• Fix security issues rather than suppressing them whenever possible
• Document clear justifications for any necessary suppressions
• Use the CheckCDKNagSuppressions tool to verify no unauthorized suppressions exist

Before applying CDK NAG Suppressions, conduct your own independent assessment to ensure compliance with your specific security and quality control practices and standards.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "awslabs-cdk-mcp-server" '{"command":"uvx","args":["awslabs.cdk-mcp-server@latest"],"env":{"FASTMCP_LOG_LEVEL":"ERROR"},"disabled":false,"autoApprove":[]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "awslabs.cdk-mcp-server": {
            "command": "uvx",
            "args": [
                "awslabs.cdk-mcp-server@latest"
            ],
            "env": {
                "FASTMCP_LOG_LEVEL": "ERROR"
            },
            "disabled": false,
            "autoApprove": []
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "awslabs.cdk-mcp-server": {
            "command": "uvx",
            "args": [
                "awslabs.cdk-mcp-server@latest"
            ],
            "env": {
                "FASTMCP_LOG_LEVEL": "ERROR"
            },
            "disabled": false,
            "autoApprove": []
        }
    }
}

3. Restart Claude Desktop for the changes to take effect