AWS Labs MCP server for AI agents

This guide explains how to install and use the Model Context Protocol (MCP) server, a tool that enhances AI assistants with AWS capabilities.

What is an AWS MCP Server?

AWS MCP servers are lightweight programs that extend AI assistants with AWS capabilities through the Model Context Protocol. They allow AI tools to access AWS documentation, services, and best practices to improve the accuracy and usefulness of AI-generated outputs.

Installation

To install and run MCP servers, you'll need to:

Install the uv package manager from Astral
Install Python using uv python install 3.10
Configure AWS credentials with appropriate permissions
Add the server to your preferred MCP client

Supported Transport Mechanisms

AWS MCP servers support:

stdio (standard input/output) - currently the only supported mechanism
Streamable HTTP (planned for future versions)

Note that Server Sent Events (SSE) support was removed as of May 26th, 2025.

Using the MCP Server

Once installed, you can configure the MCP server in your preferred client using JSON configuration. For example:

macOS/Linux Configuration

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

Windows Configuration

{
  "mcpServers": {
    "awslabs.core-mcp-server": {
      "disabled": false,
      "timeout": 60,
      "type": "stdio",
      "command": "uv",
      "args": [
        "tool",
        "run",
        "--from",
        "awslabs.core-mcp-server@latest",
        "awslabs.core-mcp-server.exe"
      ],
      "env": {
        "FASTMCP_LOG_LEVEL": "ERROR"
      }
    }
  }
}

Running in Docker Containers

Docker images for MCP servers are available in the public AWS ECR registry:

{
  "mcpServers": {
    "awslabs.nova-canvas-mcp-server": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "--interactive",
        "--env", "FASTMCP_LOG_LEVEL=ERROR",
        "--env", "AWS_REGION=us-east-1",
        "--env-file", "/full/path/to/.env",
        "--volume", "/full/path/to/.aws:/app/.aws",
        "public.ecr.aws/awslabs-mcp/awslabs/nova-canvas-mcp-server:latest"
      ],
      "env": {}
    }
  }
}

Performance Note

Using the "@latest" suffix checks for updates on each start, which increases load time. For better performance, remove "@latest" and manage your cache manually:

uv cache clean <tool>: Removes a specific tool from cache
uvx <tool>@latest: Updates a specific tool to the latest version

Client-Specific Setup

The MCP server can be configured in various AI coding assistants:

Amazon Q Developer CLI: Edit ~/.aws/amazonq/mcp.json
Kiro: Configure through Kiro > MCP Servers menu
Cline: Edit cline_mcp_settings.json
Cursor: Add configuration to .cursor/mcp.json (project-specific) or ~/.cursor/mcp.json (global)
Windsurf: Configure via Settings > Advanced Settings or edit ~/.codeium/windsurf/mcp_config.json
VS Code: Edit .vscode/mcp.json
Claude Code: Use CLI commands or edit .mcp.json

For any of these clients, you'll use the same JSON structure shown earlier, adapted to your specific environment.

When to Use Local vs. Remote Servers

Local servers are best for development, testing, offline work, and keeping sensitive data private
Remote servers are ideal for team collaboration, resource-intensive tasks, and ensuring availability

Some MCP servers, like AWS Knowledge MCP, are provided as fully managed services by AWS with no setup required.

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-core-mcp-server" '{"command":"uvx","args":["awslabs.core-mcp-server@latest"],"env":{"FASTMCP_LOG_LEVEL":"ERROR"}}'

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.core-mcp-server": {
            "command": "uvx",
            "args": [
                "awslabs.core-mcp-server@latest"
            ],
            "env": {
                "FASTMCP_LOG_LEVEL": "ERROR"
            }
        },
        "awslabs.nova-canvas-mcp-server": {
            "command": "uvx",
            "args": [
                "awslabs.nova-canvas-mcp-server@latest"
            ],
            "env": {
                "AWS_PROFILE": "your-aws-profile",
                "AWS_REGION": "us-east-1",
                "FASTMCP_LOG_LEVEL": "ERROR"
            }
        },
        "awslabs.bedrock-kb-retrieval-mcp-server": {
            "command": "uvx",
            "args": [
                "awslabs.bedrock-kb-retrieval-mcp-server@latest"
            ],
            "env": {
                "AWS_PROFILE": "your-aws-profile",
                "AWS_REGION": "us-east-1",
                "FASTMCP_LOG_LEVEL": "ERROR"
            }
        },
        "awslabs.cost-analysis-mcp-server": {
            "command": "uvx",
            "args": [
                "awslabs.cost-analysis-mcp-server@latest"
            ],
            "env": {
                "AWS_PROFILE": "your-aws-profile",
                "FASTMCP_LOG_LEVEL": "ERROR"
            }
        },
        "awslabs.cdk-mcp-server": {
            "command": "uvx",
            "args": [
                "awslabs.cdk-mcp-server@latest"
            ],
            "env": {
                "FASTMCP_LOG_LEVEL": "ERROR"
            }
        },
        "awslabs.aws-documentation-mcp-server": {
            "command": "uvx",
            "args": [
                "awslabs.aws-documentation-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.core-mcp-server": {
            "command": "uvx",
            "args": [
                "awslabs.core-mcp-server@latest"
            ],
            "env": {
                "FASTMCP_LOG_LEVEL": "ERROR"
            }
        },
        "awslabs.nova-canvas-mcp-server": {
            "command": "uvx",
            "args": [
                "awslabs.nova-canvas-mcp-server@latest"
            ],
            "env": {
                "AWS_PROFILE": "your-aws-profile",
                "AWS_REGION": "us-east-1",
                "FASTMCP_LOG_LEVEL": "ERROR"
            }
        },
        "awslabs.bedrock-kb-retrieval-mcp-server": {
            "command": "uvx",
            "args": [
                "awslabs.bedrock-kb-retrieval-mcp-server@latest"
            ],
            "env": {
                "AWS_PROFILE": "your-aws-profile",
                "AWS_REGION": "us-east-1",
                "FASTMCP_LOG_LEVEL": "ERROR"
            }
        },
        "awslabs.cost-analysis-mcp-server": {
            "command": "uvx",
            "args": [
                "awslabs.cost-analysis-mcp-server@latest"
            ],
            "env": {
                "AWS_PROFILE": "your-aws-profile",
                "FASTMCP_LOG_LEVEL": "ERROR"
            }
        },
        "awslabs.cdk-mcp-server": {
            "command": "uvx",
            "args": [
                "awslabs.cdk-mcp-server@latest"
            ],
            "env": {
                "FASTMCP_LOG_LEVEL": "ERROR"
            }
        },
        "awslabs.aws-documentation-mcp-server": {
            "command": "uvx",
            "args": [
                "awslabs.aws-documentation-mcp-server@latest"
            ],
            "env": {
                "FASTMCP_LOG_LEVEL": "ERROR"
            },
            "disabled": false,
            "autoApprove": []
        }
    }
}

3. Restart Claude Desktop for the changes to take effect