AWS Cloud Development Kit MCP server for AI agents

The AWS CDK MCP Server is a tool designed to help developers implement AWS infrastructure as code following best practices. It provides guidance on CDK patterns, security compliance through CDK Nag integration, and specialized support for Lambda layers and Bedrock Agent implementations.

Installation Prerequisites

Set Up Your Environment

Before installing the CDK MCP Server, you'll need:

Install the uv package manager:

# Follow installation instructions at 
# https://docs.astral.sh/uv/getting-started/installation/

Install Python 3.10 using uv:
```
uv python install 3.10
```
Install AWS CDK CLI:
```
npm install -g aws-cdk
```

Server Installation

Install the MCP Server

You can install the server using one of these methods:

For command line installation, configure your MCP client by editing ~/.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": []
    }
  }
}

Docker Installation

If you prefer using Docker:

Build the Docker image:

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

Configure your MCP client with Docker support:

{
  "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 specialized tools:

CDKGeneralGuidance: Get best practices for AWS CDK applications
GetAwsSolutionsConstructPattern: Find recommended architecture patterns
SearchGenAICDKConstructs: Discover constructs for AI/ML workloads
GenerateBedrockAgentSchema: Create schemas for Bedrock Agent action groups
LambdaLayerDocumentationProvider: Access Lambda layer documentation
ExplainCDKNagRule: Get guidance on security rules
CheckCDKNagSuppressions: Validate code suppressions

Recommended Workflow

The typical CDK implementation workflow with this server:

Start with CDKGeneralGuidance for general best practices
Initialize your CDK app with cdk init app
Choose your implementation approach:
- For common patterns: Use GetAwsSolutionsConstructPattern
- For GenAI features: Use SearchGenAICDKConstructs
- For custom needs: Write custom CDK code
If using Lambda functions with layers, use LambdaLayerDocumentationProvider
Run cdk synth to check for issues
Address CDK Nag warnings with ExplainCDKNagRule
Use CheckCDKNagSuppressions to review suppressions
Deploy your application with cdk deploy

Bedrock Agent Schema Generation

When creating Bedrock Agents with Action Groups using Lambda:

Create a Lambda function that uses BedrockAgentResolver from AWS Lambda Powertools
Use the GenerateBedrockAgentSchema tool to generate an OpenAPI schema
If schema generation succeeds, an openapi.json file will be created
If there are import errors, a fallback script will be generated
Install any missing dependencies and run the script again
Use the generated schema in your CDK code with bedrock.ApiSchema.fromLocalAsset()

Accessing Resources

The server provides access to various resource types:

CDK Nag Rules: cdk-nag://rules/{rule_pack}
AWS Solutions Constructs: aws-solutions-constructs://{pattern_name}
GenAI CDK Constructs: genai-cdk-constructs://{construct_type}/{construct_name}
Lambda Powertools: lambda-powertools://{topic}

Security Best Practices

When using the CDK MCP Server:

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

Always conduct your own security assessment to ensure compliance with your organization's security standards and relevant regulations.

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