Markdown Content: Amazon Bedrock Knowledge Base Retrieval MCP Server
MCP server for accessing Amazon Bedrock Knowledge Bases
Features
Discover knowledge bases and their data sources
- Find and explore all available knowledge bases
- Search for knowledge bases by name or tag
- List data sources associated with each knowledge base
Query knowledge bases with natural language
- Retrieve information using conversational queries
- Get relevant passages from your knowledge bases
- Access citation information for all results
Filter results by data source
- Focus your queries on specific data sources
- Include or exclude specific data sources
- Prioritize results from specific data sources
Rerank results
- Improve relevance of retrieval results
- Use Amazon Bedrock reranking capabilities
- Sort results by relevance to your query
Prerequisites
Installation Requirements
- Install
uvfrom Astral or the GitHub README - Install Python using
uv python install 3.10
AWS Requirements
- AWS CLI Configuration: You must have the AWS CLI configured with credentials and an AWS_PROFILE that has access to Amazon Bedrock and Knowledge Bases
- Amazon Bedrock Knowledge Base: You must have at least one Amazon Bedrock Knowledge Base with the tag key
mcp-multirag-kbwith a value oftrue - IAM Permissions: Your IAM role/user must have appropriate permissions to: * List and describe knowledge bases * Access data sources * Query knowledge bases
Reranking Requirements
If you intend to use reranking functionality, your Bedrock Knowledge Base needs additional permissions:
- Your IAM role must have permissions for both
bedrock:Rerankandbedrock:InvokeModelactions - The Amazon Bedrock Knowledge Bases service role must also have these permissions
- Reranking is only available in specific regions. Please refer to the official documentation for an up to date list of supported regions.
- Enable model access for the available reranking models in the specified region.
Controlling Reranking
Reranking can be globally 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 various formats:
- For enabling: 'true', '1', 'yes', or 'on' (case-insensitive)
- For disabling: any other value or not set (default behavior)
This setting provides a global default, while individual API calls can still override it by explicitly setting the reranking parameter.
For detailed instructions on setting up knowledge bases, see:
- Create a knowledge base
- Managing permissions for Amazon Bedrock knowledge bases
- Permissions for reranking in Amazon Bedrock
Installation
| Cursor | VS Code |
|---|---|
Configure the MCP server in your MCP client configuration (e.g., for Amazon Q Developer CLI, edit ~/.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": [] } } }
or docker after a successful docker build -t awslabs/bedrock-kb-retrieval-mcp-server .:
# fictitious `.env` file with AWS temporary credentials
AWS_ACCESS_KEY_ID=ASIAIOSFODNN7EXAMPLE
AWS_SECRET_ACCESS_KEY=wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY
AWS_SESSION_TOKEN=AQoEXAMPLEH4aoAH0gNCAPy...truncated...zrkuWJOgQs8IZZaIv2BXIa2R4Olgk
{ "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
Limitations
- Results with
IMAGEcontent type are not included in the KB query response. - The
rerankingparameter requires additional permissions, Amazon Bedrock model access, and is only available in specific regions.
Recommend MCP Servers 💡
strava
A Model Context Protocol (MCP) server with Strava OAuth integration, built on Cloudflare Workers. Enables secure authentication and tool access for MCP clients like Claude and Cursor through Strava login. Perfect for developers looking to integrate Strava authentication with AI tools.
supadata-mcp
A Model Context Protocol (MCP) server that integrates with Supadata.ai to provide powerful video transcript extraction, web scraping, crawling, and discovery capabilities for LLM clients like Cursor and Claude.
CelestialMCP
A Model Context Protocol (MCP) server providing tools to access astronomical data, including celestial object positions, rise/set times, visibility, and catalog information for AI assistants.
mcp-search-console
A Model Context Protocol (MCP) server for managing Google Search Console properties, sitemaps, and search analytics via its API
@chaindead/telegram-mcp
Telegram MCP for managing dialogs, messages, drafts, read statuses, and more.
ccassini/DEVNADS-Monad-TESNET-MCP-Tools
A Model Context Protocol server for interacting with the Monad blockchain testnet, offering features like wallet balance checking, network info, transaction details, token transfers, and staking.