awslabs.bedrock-kb-retrieval-mcp-server

What it is and what it does

This is an MCP (Model Context Protocol) server that bridges AI tools and applications to Amazon Bedrock Knowledge Bases. It exposes Bedrock knowledge bases as discoverable resources with natural-language query capabilities, allowing AI models and agents to retrieve relevant passages, filter results by data source, and optionally rerank results for improved relevance. The package wraps boto3 calls to Bedrock behind an MCP interface, so it runs as a server process that MCP-compatible clients (Kiro, Cursor, VS Code, or other tools) connect to.

The server requires AWS credentials and IAM permissions to access Bedrock and your knowledge bases. It supports filtering knowledge bases by tag, querying with conversational language, and returning citation information alongside results. Reranking is optional and controlled via environment variable or per-query parameter; it requires additional IAM permissions and is only available in certain AWS regions. The package is actively maintained, supports Python 3.10–3.13, and has no known vulnerabilities.

Use it for:

• Integrate Bedrock Knowledge Bases into AI agents or chat applications so they can retrieve and cite domain-specific information in real time.
• Query multiple knowledge bases from a single MCP client interface, filtering by data source to focus retrieval on specific document collections.
• Improve search relevance by enabling Bedrock reranking on knowledge base results when available in your region.
• Discover and explore all available knowledge bases and their data sources programmatically through an MCP server.
• Build AI assistants that combine Bedrock models with your own knowledge bases for grounded, cited responses.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

An MCP server that connects AI tools to Amazon Bedrock Knowledge Bases, enabling natural-language queries, result filtering by data source, and optional reranking of retrieved passages.

Yes, if you use Bedrock Knowledge Bases and need to expose them to AI tools via MCP. The package is actively maintained, has low install friction, permissive licensing, and zero known vulnerabilities. Install only if you have AWS credentials, appropriate IAM permissions, and at least one tagged knowledge base; otherwise, setup will fail at runtime.

Install

awslabs-bedrock-kb-retrieval-mcp-server on PyPI

pip install awslabs-bedrock-kb-retrieval-mcp-server

uv add awslabs-bedrock-kb-retrieval-mcp-server

poetry add awslabs-bedrock-kb-retrieval-mcp-server

Installing awslabs.bedrock-kb-retrieval-mcp-server

Before you install

Low friction: pure Python wheel with four lightweight runtime dependencies (boto3, loguru, mcp, pydantic). Active maintenance—released 4 days ago with 9599 repository stars and continuous updates since April 2025.

License in practice

Apache-2.0 permissive license allows commercial and private use with minimal restrictions; suitable for most projects.

Quickstart

# Install via uv
uv pip install awslabs.bedrock-kb-retrieval-mcp-server

# Configure in MCP client (e.g., ~/.kiro/settings/mcp.json)
# Set AWS_PROFILE, AWS_REGION, and optional BEDROCK_KB_RERANKING_ENABLED

# Then use via MCP client to query knowledge bases

Requires Python >=3.10; AWS CLI configured with credentials and IAM permissions for bedrock:InvokeModel and bedrock:DescribeKnowledgeBase; at least one Bedrock Knowledge Base tagged with mcp-multirag-kb=true.

Verify before relying

• Whether reranking is available in all AWS regions or only specific ones (description mentions 'specific regions' but does not list them).
• Whether the package works as a standalone library or only as an MCP server within a compatible client.
• Performance characteristics when querying large knowledge bases or handling many concurrent requests.

Package facts

Evidence: awslabs_bedrock_kb_retrieval_mcp_server-1.0.25-py3-none-any.whl

Tags

More Artificial Intelligence packages

Further reading