How to Use the Bing Search MCP in Mastra AI

Q: Can I require human approval before Mastra AI executes a Bing Search?

Yes. You can configure requireToolApproval in your Mastra AI agent config for the searchlocal tool. The workflow pauses until a human approves the search query.

Q: Does Mastra AI support autocomplete suggestions from Bing?

Yes. Your agent can call searchsuggestions to get autocomplete options. You can use this inside a workflow step to refine a user's raw query before running a full search.

Build resilient multi-step search workflows using Mastra AI and the Bing Search MCP Server.

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 Mastra AI

Create your Vinkius account to connect Bing Search 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 Bing Search with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Branching Workflows Guided by Web Search

The `search_web` tool feeds real-time context directly into your Mastra AI workflow steps via this MCP Server. If a web search returns zero results, Mastra's routing logic can instantly branch to a secondary query or trigger a fallback mechanism. This lets your Mastra agents make branching logic decisions based on live Bing search results. You can inspect the web search results programmatically inside Mastra's workflow engine and choose different execution paths.

Automated Local Discovery with MCP Server Retries

The `search_local` tool queries physical businesses and coordinates to feed your location-based Mastra AI agents. If the API hits a temporary rate limit, Mastra's built-in exponential backoff automatically retries the search until it succeeds. You don't have to write custom retry loops for failed Bing Local queries. The workflow engine keeps trying the local lookup in the background while your main loop keeps running.

Safe News Aggregation Pipelines

The `search_news` tool retrieves breaking articles that your Mastra AI agents can filter and summarize. By setting up human-in-the-loop approval, you can require a developer to sign off on the gathered news before it gets published. If the agent wants to find video context, it can call `search_videos` in a parallel workflow step. Mastra handles the async execution of both tools and combines the media data into a single payload.

Setup guide

Set up Bing Search 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 Bing Search 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: "bing-search-mcp-client",
  servers: {
    "bing-search-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent Bing Search 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 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 Mastra AI

Mastra AI has built-in retry logic with exponential backoff. If the `search_web` tool gets rate-limited by the API, the framework will pause and try again automatically before failing the workflow step.

Yes. You can configure `requireToolApproval` in your Mastra AI agent config for the `search_local` tool. The workflow pauses until a human approves the search query.

You deploy your Mastra AI agent to any cloud provider using their CLI. Vinkius hosts the MCP Server, so your deployed agent just needs the connection URL to start searching.

Yes. Your agent can call `search_suggestions` to get autocomplete options. You can use this inside a workflow step to refine a user's raw query before running a full search.

The server processes your search terms and location queries inside an isolated V8 sandbox. Your search parameters are never cached on disk, ensuring your workflow data remains private.

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