How to Use the Bing Search MCP in Vercel AI SDK

Q: Can I stream Bing Search image results to Vercel AI SDK components?

Yes, easily. When your agent invokes searchimages, the server returns structured pixel dimensions and thumbnail URLs that you can stream directly to your frontend to render standard image components instantly.

Q: How do I restrict Bing Search queries to specific domains in my Vercel AI SDK setup?

Use the customsearch tool. You pass your pre-built configuration ID through your tool call, which locks the agent's queries strictly to your whitelisted domains instead of the open web.

Feed live Microsoft Bing Graph data straight into your Vercel AI SDK stream without blocking the UI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bing Search MCP to Vercel AI SDK

Create your Vinkius account to connect Bing Search 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 Bing Search with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed live search results to your React components

The `search_web` tool lets your Vercel AI SDK application stream live organic results from the Microsoft Graph directly to the client UI. Your users hate waiting for spinners while your agent fetches web data. You can render rich UI cards instantly using the structured JSON returned by `search_images` or `search_videos`. Because this runs natively in Edge Functions, your app stays fast while the agent grabs pixel dimensions and streaming links for the user.

Instantly fix user typos before querying the Bing MCP Server

The `spellcheck` tool cleans up messy user inputs inside your Vercel AI SDK stream to fix semantic NLP boundaries on the fly. Raw user inputs are messy, which ruins vector searches and API calls. Once cleaned, feed the polished tokens directly into `autosuggest` to predict what they want next. This keeps your edge-rendered search bars responsive without forcing the user to retype their queries.

Inject real-time news into your Vercel AI SDK context

The `search_news` tool pulls syndicated global PR articles grouped by timestamp directly into your Vercel AI SDK application. Static training data cannot tell your application what happened ten minutes ago. Your agent then parses this fresh context to answer time-sensitive prompts. It lets you build news dashboards where the latest viral topics render live without stale database reads.

Setup guide

Set up Bing Search 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 Bing Search 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 Bing Search 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 Bing Search. 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 Bing Search 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 Bing Search MCP in Vercel AI SDK

You handle it at the Edge. The server processes your requests, but you should wrap your search calls in standard middleware to throttle requests from spammy clients before they hit the Microsoft Graph.

Yes, easily. When your agent invokes `search_images`, the server returns structured pixel dimensions and thumbnail URLs that you can stream directly to your frontend to render standard image components instantly.

It does. Since Vinkius hosts the server, your code only makes lightweight HTTP fetches to our endpoint, keeping your Edge runtime light and under memory limits.

Use the `custom_search` tool. You pass your pre-built configuration ID through your tool call, which locks the agent's queries strictly to your whitelisted domains instead of the open web.

Your raw search queries and configuration IDs only pass through an ephemeral, zero-trust V8 sandbox. We never log or store the text of your searches, sending them directly to the API and back to your edge function.

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