awslabs.bedrock-kb-retrieval-mcp-server
An AWS Labs Model Context Protocol (MCP) server for Bedrock Knowledge Base Retrieval
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- 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.
- 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 · maintenance · safety
Apache-2.0 (permissive) — Apache-2.0 permissive license allows commercial and private use with minimal restrictions; suitable for most projects.
last release 2026-08-10 (4 days) · last repo commit 2026-08-14 · 9,599 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 82,853 downloads/mo, #14,123 on PyPI
Alternatives
Verify before relying
# 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- 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.
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 on it.
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
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.
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.
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 basesVerify 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
| License | Apache-2.0 permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 4 packagesboto3logurumcppydantic |
| Maintenance | Actively maintained 4 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 82,853 / month, #14,123 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | License :: OSI Approved :: Apache Software LicenseOperating System :: OS IndependentProgramming Language :: PythonProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13 |
Evidence: awslabs_bedrock_kb_retrieval_mcp_server-1.0.25-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “bedrock knowledge base retrieval”
- awslabs.bedrock-kb-retrieval-mcp-serverAn MCP server that connects AI tools to Amazon Bedrock Knowledge…
- strands-agents-builderStrands Agent Builder is a terminal-based toolkit for building,…
- neo4j-graphragBuilds graph retrieval-augmented generation (GraphRAG) applications…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also awslabs.aws-documentation-mcp-server · awslabs.redshift-mcp-server · awslabs.aws-pricing-mcp-server · awslabs.aws-api-mcp-server · awslabs.eks-mcp-server · aws-bedrock-token-generator · aws_sdk_bedrock_runtime · awslabs.cloudwatch-mcp-server · awslabs.billing-cost-management-mcp-server · bedrock-agentcore-starter-toolkit