Amazon Bedrock KB

Amazon Bedrock KB MCP Connector for Claude

A+

Connect your AI agent to AWS Bedrock Knowledge Bases — execute semantic searches, managed RAG, and sync vector datasources natively.

6 tools Official Updated Jun 28, 2026 Official Vinkius Partner

Connect your Amazon Bedrock account to any AI agent and empower it with managed vector databases, enterprise RAG workflows, and semantic search directly inside AWS.

What you can do

  • Managed RAG — Generate grounded LLM responses using internal document sets in a single explicit call
  • Semantic Retrieval — Query vector indexes to retrieve exact top-K text chunks and their origin document URLs
  • Data Sources — Inspect and paginate attached storage buckets feeding the knowledge base
  • Ingestion Jobs — Track real-time syncing status of chunking pipelines mapping documents across the vector layout
  • Knowledge Base Introspection — List available vector stores and exact embedding models assigned directly to your region

How it works

  1. Subscribe to this server
  2. Enter your AWS IAM Role/User Access Credentials
  3. Start augmenting your agent's context from Claude, Cursor, or any MCP-compatible client

Eliminate the need to build custom vector pipelines. Your agent queries massive corporate datasets precisely where they reside in AWS.

Who is this for?

  • AI Developers — build RAG workflows rapidly without hosting databases or maintaining chunking sync logic
  • Cloud Architects — audit ingestion status and check origin document mappings securely from your chat interface
  • Data Scientists — prototype context-grounded queries instantly and trace accuracy against exact data chunks
ragsemantic-searchvector-searchfoundation-modelsdata-retrievalcloud-infrastructure

6 tools expose this connector's capabilities to your AI agent.

list_knowledge_bases

List AWS Bedrock knowledge bases

get_knowledge_base

Get an explicit AWS Bedrock knowledge base

retrieve

Query a vector index securely via AWS Bedrock

retrieve_and_generate

Generate explicitly grounded LLM responses using Bedrock KB

list_data_sources

List Data Sources bound explicitly to an AWS Bedrock KB

list_ingestion_jobs

List AWS Bedrock KB explicit sync operations

See how to talk to your AI agent using Amazon Bedrock KB.

Which knowledge bases and embedding models do I have setup?

You have 1 Knowledge Base matching your region: 'Internal Wiki KB' (ID: ABCDE12345). It is mapped to the standard AWS Titan Text v2 embedding model and active for incoming syncs.

Run a retrieval query for 'onboarding process checklist' on my KB and show me the top 3 snippets.

I retrieved 3 matches from your KB. Segment 1 (from s3://hr-docs/onboarding.pdf) states: 'Ensure HR syncs Slack accounts within 24h...' Segment 2 (from s3://hr-docs/it-protocols.docx) mentions hardware issuance. Segment 3 highlights the welcome email template.

Check the status of the S3 ingestion job for my Documentation bucket.

The ingestion job for Data Source ID XYZ098 on Knowledge Base ABCDE12345 completed successfully today at 08h30. 15 new documents were chunked and mapped to the index without errors.

Yes! Use the `retrieve_and_generate` capability. Your agent passes the query and a designated Bedrock model ARN. Bedrock handles fetching chunks from the local vector index and synthesizing the final answer inside AWS boundaries, returning a fully grounded response instantly.

Related Connectors