AUTOMATIONSWITCH
OfficialAI / ML

Amazon Bedrock Knowledge Base MCP

by AWS Labs

Official AWS Labs MCP for Bedrock Knowledge Base retrieval: discover knowledge bases, query with natural language, filter by data source, and rerank results. Apache-2.0 within awslabs/mcp monorepo. Tight tool surface focused on RAG over AWS-managed KBs.

8,924·4 tools·Released APR 2025·Apache-2.0
uvx awslabs.bedrock-kb-retrieval-mcp-server@latest
Share:

Official AWS Labs MCP for Bedrock Knowledge Base retrieval: discover knowledge bases, query with natural language, filter by data source, and rerank results. 3 commits on the server path in the last 30 days. Tool surface stays tight: discover, query, filter, rerank. Carries IAM permissions through to the host AWS account.

Reviewed by M. Nouriel · MAY 2026

INSTALL THIS SERVER

Requires authenticationAWS credentials chain (AWS_PROFILE, environment, or instance role). IAM permissions required: bedrock:Retrieve on KB, optional bedrock:InvokeModel on reranker model.
{ "mcpServers": { "awslabs.bedrock-kb-retrieval-mcp-server": { "command": "uvx", "args": [ "awslabs.bedrock-kb-retrieval-mcp-server@latest" ], "env": { "AWS_PROFILE": "default", "AWS_REGION": "us-east-1" } } } }
PrereqRequires uv installed and an AWS profile with Bedrock KB IAM permissions. PyPI package: `awslabs.bedrock-kb-retrieval-mcp-server`. Bedrock Knowledge Bases must exist in the target region. Path: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS).
{ "mcpServers": { "awslabs.bedrock-kb-retrieval-mcp-server": { "command": "uvx", "args": [ "awslabs.bedrock-kb-retrieval-mcp-server@latest" ], "env": { "AWS_PROFILE": "default", "AWS_REGION": "us-east-1" } } } }
{ "mcpServers": { "awslabs.bedrock-kb-retrieval-mcp-server": { "command": "uvx", "args": [ "awslabs.bedrock-kb-retrieval-mcp-server@latest" ], "env": { "AWS_PROFILE": "default", "AWS_REGION": "us-east-1" } } } }
{ "mcpServers": { "awslabs.bedrock-kb-retrieval-mcp-server": { "command": "uvx", "args": [ "awslabs.bedrock-kb-retrieval-mcp-server@latest" ], "env": { "AWS_PROFILE": "default", "AWS_REGION": "us-east-1" } } } }
{ "mcpServers": { "awslabs.bedrock-kb-retrieval-mcp-server": { "command": "uvx", "args": [ "awslabs.bedrock-kb-retrieval-mcp-server@latest" ], "env": { "AWS_PROFILE": "default", "AWS_REGION": "us-east-1" } } } }

4 TOOLS AVAILABLE

discover_knowledge_bases
List available KBs and their data sources
Read
retrieve
Natural-language query against a chosen KB
Read
retrieve_with_filter
Query with data-source filtering
Read

OUR ASSESSMENT

Strengths
  • Apache-2.0 licence.
  • Official AWS Labs maintenance.
  • Reranking support via Bedrock reranker models (separate IAM permission).
  • Filter by data source for multi-source KBs.
  • Five-client config coverage via awslabs/mcp install instructions.
Weaknesses
  • 3 commits on the path in the last 30 days, lower cadence than the parent monorepo headline figure.
  • Image content from KBs is excluded from query results.
  • Requires Bedrock KB and (optionally) reranker IAM permissions on the host account.
  • Pricing is the AWS Bedrock pricing model (per-request; reranker requests are priced separately).
Security Notes

The server uses the host AWS credentials chain to query Bedrock KBs. Scope the IAM role to the specific KB IDs the agent should access; deny wildcard ARNs. Reranking adds a separate IAM permission boundary (Bedrock model invocation). For production agents, run the MCP under a dedicated AWS profile with read-only KB access and explicit reranker model allow-lists.

Best For

Teams with content already indexed in Bedrock Knowledge Bases who want agents to retrieve and cite from the same KB the production application uses; RAG workflows where retrieval lives inside AWS for compliance reasons (data residency, IAM-scoped access); operators evaluating Bedrock reranking models against a base KB query baseline.

TECHNICAL DETAILS

Language
python
Transport
stdio
Clients
Claude DesktopClaude CodeCursorVS CodeWindsurf
License
Apache-2.0
GitHub
awslabs/mcp · ★ 8,924
npm
awslabs.bedrock-kb-retrieval-mcp-server
Last Release
awslabs.bedrock-kb-retrieval-mcp-server (PyPI)MAY 1, 2026
First Released
APR 1, 2025

ADOPTION METRICS

// GitHub Stars
8,924

// Reading this8,924 stars on the awslabs/mcp parent monorepo. 3 commits on the Bedrock KB server path in the last 30 days.

// Popularity Rank
#4
Globally · #4 in AI / ML

// Reading thisFourth-ranked in ai-ml. Tier 2 cadence; Tier 1 vendor signal.

SOURCES & VERIFICATION

We don't take any single directory's word for it. Before scoring, we cross-reference 5 public MCP sources, install the server ourselves against the clients we cover, and record when we last re-verified.

01
Discovered
Manual submission
First indexed MAY 1, 2026
02
Cross-referenced
5 directories
PulseMCP, MCP.so, Glama, Smithery, Official MCP Registry
03
Verified against
Claude Desktop, Cursor (per awslabs/mcp install instructions)
Installed and tested across clients
04
Last re-checked
MAY 1, 2026
Weekly re-verification
// How other directories see it

The same server, 5 different lenses. We reconcile these signals into our editorial score, which is why our number sometimes diverges from a directory-aggregate star count.

SourceTheir ratingTheir star countTheir downloadsLast synced
AutomationSwitch This page4.1editorial8,924MAY 1, 2026
PulseMCP— unratedunavailableunavailableMAY 1, 2026
MCP.so— unratedunavailableunavailableMAY 1, 2026
Glama— unratedunavailableunavailableMAY 1, 2026
Smithery— unratedunavailableunavailableMAY 1, 2026
Official MCP Registry— unratedunavailableunavailableMAY 1, 2026

// Counts are directory-reported; we don't adjust them. Discrepancies usually come from different snapshot times or star-caching.

OTHER AI / ML MCP SERVERS

Community4.6

Cognee MCP

topoteretes

Knowledge graph plus vector memory engine for AI agents, exposed as an MCP server with V2 session-aware memory tools (remember, recall, forget, improve) and classic V1 ingestion pipelines (cognify, codify). Three transports: stdio, SSE, Streamable HTTP. 16,965 GitHub stars, Apache-2.0.

8 tools16,965
Community4.6

Codebase Memory MCP

DeusData

High-performance code intelligence MCP server for AI coding agents. Indexes a codebase into a queryable knowledge graph in milliseconds, with 14 MCP tools spanning structural search, call-chain tracing, impact analysis, dead-code detection, and Cypher queries. Single static C binary, 66 languages via tree-sitter, zero runtime dependencies.

9 tools1,929
Vendor4.5

Arize Phoenix MCP

Arize AI

LLM observability platform exposing prompts, projects, traces, spans, sessions, datasets, and experiments through MCP. Published to npm as @arizeai/phoenix-mcp, current 4.0.8 (2026-04-29). 9,496 stars on parent monorepo, Elastic License 2.0.

8 tools9,496
Vendor4.5

Qdrant MCP Server

Qdrant

Official Qdrant vector database MCP server. Acts as a semantic memory layer on top of Qdrant: store information with metadata, retrieve via similarity search. Two tools, very small surface area, exceptionally maintained by the Qdrant team. Configurable embedding provider (fastembed default), supports remote and local Qdrant clusters.

2 tools1,373
Official4.4

Amazon Bedrock AgentCore MCP

AWS Labs

Official AWS Labs MCP server for Amazon Bedrock AgentCore: agent runtime, memory, gateway, identity, and observability. Tools fetch curated AgentCore documentation and surface deployment guides for runtime, memory, and gateway resources. Apache-2.0 within awslabs/mcp monorepo (8,924 parent stars).

5 tools8,924
Vendor4.3

ElevenLabs MCP

ElevenLabs

Official ElevenLabs MCP server. Wraps the full ElevenLabs API surface: text-to-speech, voice cloning, speech-to-text, dubbing, sound effect generation, audio isolation, voice design. MIT-licensed, distributed via PyPI as elevenlabs-mcp. Free tier with 10,000 credits per month.

7 tools1,333
// Get in touch

DISCUSS YOUR
MCP REQUIREMENTS.

Evaluating a server, scoping an internal deployment, or working out whether MCP is the right fit at all. Start the conversation and we will point you at the right piece of the ecosystem.

Discuss Your MCP Requirements →