How to Use the Amazon Bedrock KB MCP in Vercel AI SDK

Q: How do I stream answers from Amazon Bedrock KB in my Vercel AI SDK app?

Use the retrieveandgenerate tool. It combines the search and generation steps into one call, and the Vercel AI SDK's streamText function will render the response token-by-token in your UI.

Q: Can I see which data sources are connected to Amazon Bedrock KB using the Vercel AI SDK?

Yes, that's what the listdatasources tool is for. You can call it from your frontend code to get a list of all data sources for a specific knowledge base. It's perfect for building admin dashboards.

Q: Does this work with Next.js and the Vercel AI SDK?

Absolutely. You install the @ai-sdk/mcp package and point it to your Vinkius endpoint. The tools become available to generateText and streamText in your Route Handlers or Server Components.

Q: How can I debug sync issues between my data and Amazon Bedrock KB with the Vercel AI SDK?

The listingestionjobs tool is your best bet. It shows a history of sync operations, including their status. You can call it from an internal tool built with the Vercel AI SDK to quickly spot any failed jobs.

Stream grounded AI answers from Amazon Bedrock KB directly into your Vercel AI SDK app, live.

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 Vercel AI SDK

Create your Vinkius account to connect Amazon Bedrock KB to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Bedrock KB Results

Use `retrieve_and_generate` to feed grounded responses from your knowledge base straight into your React or Svelte components. The Vercel AI SDK streams the text as it's generated. Your users see the answer appear word-by-word, not after a spinner. For more control, call `retrieve` first to get the raw vector search results. You can display the source documents in your UI while `generateText` builds the final answer. It's a better user experience, and this MCP Server makes it simple.

Inspect Your Knowledge Base

This isn't just for querying. You can build internal admin panels that give a live look into your Bedrock setup. Use `list_knowledge_bases` to show all available KBs, then let users drill down with `get_knowledge_base`. Check the status of your data syncs with `list_ingestion_jobs` and see what's connected with `list_data_sources`. Since the Vercel AI SDK is Edge Function compatible, you can build a lightweight dashboard that talks to this server without a dedicated backend.

Grounded AI for the Vercel AI SDK

Stop your AI from making things up. The `retrieve_and_generate` tool forces the LLM to base its answers only on documents from your Amazon Bedrock KB. You get trustworthy responses backed by your own data. This is a managed Retrieval-Augmented Generation (RAG) setup. You don't have to build the vector pipeline yourself. Just connect this MCP server to your app, and your agent can perform semantic searches and generate accurate text.

Setup guide

Set up Amazon Bedrock KB MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Amazon Bedrock KB tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Amazon Bedrock KB transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Use the `retrieve_and_generate` tool. It combines the search and generation steps into one call, and the Vercel AI SDK's `streamText` function will render the response token-by-token in your UI.

Yes, that's what the `list_data_sources` tool is for. You can call it from your frontend code to get a list of all data sources for a specific knowledge base. It's perfect for building admin dashboards.

Absolutely. You install the `@ai-sdk/mcp` package and point it to your Vinkius endpoint. The tools become available to `generateText` and `streamText` in your Route Handlers or Server Components.

The `list_ingestion_jobs` tool is your best bet. It shows a history of sync operations, including their status. You can call it from an internal tool built with the Vercel AI SDK to quickly spot any failed jobs.

The server processes your query text and the content from your Bedrock KB data sources. Vinkius uses an ephemeral, zero-trust sandbox for every request. Nothing is stored, and your AWS credentials are never exposed to the 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