How to Use the Amazon Bedrock KB MCP in Mastra AI

Q: How do I build a multi-step RAG process for Amazon Bedrock KB using Mastra AI?

First, call retrieve to fetch context. Then, use Mastra AI's conditional logic to analyze the results before calling retrieveandgenerate. This lets you filter sources or add information before the final answer is created.

Q: What's the best way to list all my Amazon Bedrock KB instances in a Mastra AI script?

Just call the listknowledgebases tool. It returns an array of all KBs in your account, which you can then loop through in your workflow for reporting or validation tasks.

Q: Can I require human approval for certain Bedrock queries in Mastra AI?

Yes. Mastra AI supports requireToolApproval. You could design a workflow where a call to retrieveandgenerate for sensitive topics pauses execution and waits for a person to approve it.

Build resilient workflows that query and manage your Amazon Bedrock KB with Mastra AI's workflow engine.

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 Mastra AI

Create your Vinkius account to connect Amazon Bedrock KB to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Reliable KB Workflows

This MCP Server exposes the tools you need to automate your Bedrock KB management. A Mastra AI workflow can trigger an ingestion job, then use `list_ingestion_jobs` to poll for completion. If it fails, Mastra's engine can automatically retry or escalate. You can build a workflow that checks all your KBs daily. It would use `list_knowledge_bases` to get the list, then loop through each one using `list_data_sources` to confirm the right sources are attached. It's set-and-forget monitoring for your RAG pipeline.

Add Smarter RAG to Mastra AI Agents

Go beyond simple Q&A. With Mastra AI, you can build conditional logic around Bedrock KB queries. Use the `retrieve` tool to get source documents and check their metadata before deciding whether to proceed with generation. For example, if a query returns documents marked 'confidential,' your workflow could route the request for human approval instead of automatically generating an answer with `retrieve_and_generate`. That's the kind of robust process Mastra AI is built for.

A Resilient MCP Server Connection

This isn't just a basic API wrapper. The Mastra AI client has built-in support for things like exponential backoff. If a call to `get_knowledge_base` fails due to a transient network issue, the client handles the retries for you. You define the workflow, and Mastra AI's engine handles the execution details. By pairing it with this managed MCP server, you get a reliable way to interact with AWS services without writing tons of boilerplate error-handling code.

Setup guide

Set up Amazon Bedrock KB MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Amazon Bedrock KB tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "amazon-bedrock-kb-mcp-client",
  servers: {
    "amazon-bedrock-kb-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Amazon Bedrock KB Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Amazon Bedrock KB tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Amazon Bedrock KB transactions"
);
console.log(result.text);

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 Mastra AI

Yes, that's a perfect job for a Mastra AI workflow. Use the `list_ingestion_jobs` tool and check the status of the latest job. You can build logic to retry or notify an admin on failure.

First, call `retrieve` to fetch context. Then, use Mastra AI's conditional logic to analyze the results before calling `retrieve_and_generate`. This lets you filter sources or add information before the final answer is created.

Just call the `list_knowledge_bases` tool. It returns an array of all KBs in your account, which you can then loop through in your workflow for reporting or validation tasks.

Yes. Mastra AI supports `requireToolApproval`. You could design a workflow where a call to `retrieve_and_generate` for sensitive topics pauses execution and waits for a person to approve it.

The server only handles your query text and the data retrieved from your Bedrock KB for the duration of a single operation. Each request runs in its own isolated Vinkius sandbox, and the environment is torn down immediately after. Your AWS keys stay secure and are never sent to the Mastra AI client.

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