AWS Bedrock Knowledge Base Retrieval MCP server

The Amazon Bedrock Knowledge Base MCP Server provides a seamless way to access and query Amazon Bedrock Knowledge Bases through a Model Context Protocol server. It allows you to discover knowledge bases, retrieve information with natural language queries, and enhance search results through filtering and reranking capabilities.

Prerequisites

Installation Requirements

Before getting started, you'll need:

1. Install uv from Astral or the GitHub README
2. Install Python using uv python install 3.10

AWS Requirements

1. AWS CLI Configuration: Configure AWS CLI with credentials and an AWS_PROFILE that has access to Amazon Bedrock and Knowledge Bases
2. Amazon Bedrock Knowledge Base: Have at least one Amazon Bedrock Knowledge Base with the tag key mcp-multirag-kb with a value of true
3. IAM Permissions: Your IAM role/user needs permissions to:
   • List and describe knowledge bases
   • Access data sources
   • Query knowledge bases

Reranking Requirements

For reranking functionality:

1. Your IAM role must have permissions for both bedrock:Rerank and bedrock:InvokeModel actions
2. The Amazon Bedrock Knowledge Bases service role must have these permissions too
3. Reranking is only available in specific regions - check the official documentation
4. Enable model access for available reranking models in your region

Installation

Using MCP with Amazon Q Developer CLI

Configure the MCP server in your config file (e.g., ~/.aws/amazonq/mcp.json):

{
  "mcpServers": {
    "awslabs.bedrock-kb-retrieval-mcp-server": {
      "command": "uvx",
      "args": ["awslabs.bedrock-kb-retrieval-mcp-server@latest"],
      "env": {
        "AWS_PROFILE": "your-profile-name",
        "AWS_REGION": "us-east-1",
        "FASTMCP_LOG_LEVEL": "ERROR",
        "KB_INCLUSION_TAG_KEY": "optional-tag-key-to-filter-kbs",
        "BEDROCK_KB_RERANKING_ENABLED": "false"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

Using Docker

First, build the Docker image:

docker build -t awslabs/bedrock-kb-retrieval-mcp-server .

Create a .env file with your AWS credentials:

AWS_ACCESS_KEY_ID=ASIAIOSFODNN7EXAMPLE
AWS_SECRET_ACCESS_KEY=wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY
AWS_SESSION_TOKEN=AQoEXAMPLEH4aoAH0gNCAPy...truncated...zrkuWJOgQs8IZZaIv2BXIa2R4Olgk

Configure the MCP server in your MCP configuration file:

{
  "mcpServers": {
    "awslabs.bedrock-kb-retrieval-mcp-server": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "--interactive",
        "--env",
        "FASTMCP_LOG_LEVEL=ERROR",
        "--env",
        "KB_INCLUSION_TAG_KEY=optional-tag-key-to-filter-kbs",
        "--env",
        "BEDROCK_KB_RERANKING_ENABLED=false",
        "--env",
        "AWS_REGION=us-east-1",
        "--env-file",
        "/full/path/to/file/above/.env",
        "awslabs/bedrock-kb-retrieval-mcp-server:latest"
      ],
      "env": {},
      "disabled": false,
      "autoApprove": []
    }
  }
}

Note: Your credentials will need to be kept refreshed from your host.

Configuration Options

Controlling Reranking

Reranking can be enabled or disabled using the BEDROCK_KB_RERANKING_ENABLED environment variable:

• Set to false (default): Disables reranking for all queries unless explicitly enabled
• Set to true: Enables reranking for all queries unless explicitly disabled

The environment variable accepts:

• For enabling: 'true', '1', 'yes', or 'on' (case-insensitive)
• For disabling: any other value or not set (default behavior)

Individual API calls can override this setting by explicitly setting the reranking parameter.

Limitations

• Results with IMAGE content type are not included in the KB query response
• The reranking parameter requires additional permissions, Amazon Bedrock model access, and is only available in specific regions

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.