How to Use the Amazon Bedrock KB MCP in Claude

Q: How do I run a search in Amazon Bedrock KB using Claude Desktop?

You type your query in the chat, and Claude Desktop calls retrieve to query your AWS vector index. The server returns the most relevant document chunks directly into your local chat window.

Q: Can I trigger a sync for Amazon Bedrock KB from Claude Desktop using this MCP Server?

You can monitor sync status using listingestionjobs to see if your S3 data is processed. To kick off a new sync, you manage the data source inside AWS, then use Claude Desktop to verify the ingestion status.

Q: How does Claude Desktop choose which Amazon Bedrock KB to query?

Claude Desktop uses listknowledgebases to see what is available in your AWS configuration. You tell Claude which specific index to query, and it targets that ID for all subsequent retrieve calls.

Pull live AWS enterprise data into Claude Desktop to run grounded semantic searches without leaving your chat.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Amazon Bedrock KB MCP to Claude Desktop

Create your Vinkius account to connect Amazon Bedrock KB to Claude Desktop and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Amazon Bedrock KB with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ground Claude Desktop chats in Bedrock KB data

The `retrieve_and_generate` tool pulls grounded answers directly from your AWS Bedrock vector stores into your Claude Desktop chat window. Instead of copying and pasting documents, this MCP Server lets Claude query your company's official knowledge base so you don't have to guess. This connection bypasses manual searches by letting Claude Desktop trigger `retrieve` to fetch raw text chunks from your active index. Your local Claude app handles the formatting, giving you verified answers backed by your exact AWS configurations.

Monitor AWS data ingestion inside your local sidebar

The `list_ingestion_jobs` tool lets Claude Desktop track active sync operations for your AWS data sources. When you upload new files to your S3 buckets, you'll ask Claude to check the status rather than logging into the AWS Console. By invoking `list_data_sources`, your local client maps out exactly which data pipelines feed into your index using this MCP connection. This gives you instant visibility into whether your local changes have processed through the Bedrock pipeline.

Map Bedrock knowledge bases from Claude Desktop

The `list_knowledge_bases` tool queries your AWS account to display every active Bedrock index inside your Claude Desktop session. You can switch contexts instantly because Claude's ready to target a specific index for your next prompt. Once you identify the correct index, the `get_knowledge_base` tool fetches its exact configuration details. This ensures your local client uses the correct model mappings and vector dimensions for every query.

Setup guide

Set up Amazon Bedrock KB MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Amazon Bedrock KB MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Amazon Bedrock KB MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under amazon-bedrock-kb-mcp.

json

{
  "mcpServers": {
    "amazon-bedrock-kb-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Amazon Bedrock. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Amazon Bedrock KB now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Amazon Bedrock KB MCP in Claude Desktop

You type your query in the chat, and Claude Desktop calls `retrieve` to query your AWS vector index. The server returns the most relevant document chunks directly into your local chat window.

You can monitor sync status using `list_ingestion_jobs` to see if your S3 data is processed. To kick off a new sync, you manage the data source inside AWS, then use Claude Desktop to verify the ingestion status.

Claude Desktop uses `list_knowledge_bases` to see what is available in your AWS configuration. You tell Claude which specific index to query, and it targets that ID for all subsequent `retrieve` calls.

No. The MCP Server handles the AWS SDK calls on your behalf, so Claude Desktop only needs your Vinkius token to communicate with Bedrock.

Your AWS Bedrock vector indexes and knowledge base documents never touch Vinkius storage. Claude Desktop routes your queries through an encrypted V8 sandbox using our secure MCP Server architecture, sending raw text chunks directly to your local chat session without caching them.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript