AWS Bedrock: Knowledge Base MCP server

This MCP server lets you retrieve information from AWS Knowledge Base using Bedrock Agent Runtime. It provides a retrieval-augmented generation (RAG) system that fetches relevant content based on your queries.

Installation and Setup

Prerequisites

• AWS account with access to Bedrock Agent Runtime
• AWS credentials (access key ID, secret access key, and region)
• Docker (for container-based installation) or Node.js (for NPX-based installation)

Setting up AWS Credentials

1. Obtain your AWS access key ID, secret access key, and region from the AWS Management Console
2. Ensure these credentials have appropriate permissions for Bedrock Agent Runtime operations

Configuration with Claude Desktop

Add the server configuration to your claude_desktop_config.json file using one of the following methods:

Docker Method

{
  "mcpServers": {
    "aws-kb-retrieval": {
      "command": "docker",
      "args": [ "run", "-i", "--rm", "-e", "AWS_ACCESS_KEY_ID", "-e", "AWS_SECRET_ACCESS_KEY", "-e", "AWS_REGION", "mcp/aws-kb-retrieval-server" ],
      "env": {
        "AWS_ACCESS_KEY_ID": "YOUR_ACCESS_KEY_HERE",
        "AWS_SECRET_ACCESS_KEY": "YOUR_SECRET_ACCESS_KEY_HERE",
        "AWS_REGION": "YOUR_AWS_REGION_HERE"
      }
    }
  }
}

NPX Method

{
  "mcpServers": {
    "aws-kb-retrieval": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-aws-kb-retrieval"
      ],
      "env": {
        "AWS_ACCESS_KEY_ID": "YOUR_ACCESS_KEY_HERE",
        "AWS_SECRET_ACCESS_KEY": "YOUR_SECRET_ACCESS_KEY_HERE",
        "AWS_REGION": "YOUR_AWS_REGION_HERE"
      }
    }
  }
}

Using the Server

Available Tools

The server provides a retrieval tool with the following parameters:

• retrieve_from_aws_kb
  • Inputs:
    • query (string): Your search query for retrieval
    • knowledgeBaseId (string): The ID of your AWS Knowledge Base
    • n (number, optional): Number of results to retrieve (default: 3)

Usage Examples

When using Claude with this MCP server configured, you can prompt Claude to retrieve information from your AWS Knowledge Base by referring to the tool:

1. First, ensure Claude has access to your AWS Knowledge Base ID
2. Ask Claude to search for specific information, for example:
   • "Use the retrieve_from_aws_kb tool to find information about EC2 instances in my AWS documentation"
   • "Search my AWS Knowledge Base for information about IAM roles"

Claude will then use the MCP server to query your AWS Knowledge Base and incorporate the retrieved information into its response.

Building from Source (Docker)

If you need to build the Docker image yourself:

docker build -t mcp/aws-kb-retrieval -f src/aws-kb-retrieval-server/Dockerfile .

How to add this MCP server to 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 > MCP and click "Add new global MCP server".

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

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

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 explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.