How to Use the Bing Search MCP in OpenAI Agents SDK

Q: Can I trace Bing Search tool calls in the OpenAI Agents SDK dashboard?

Yes, every execution of searchlocal or searchvideos shows up in your run traces. You can inspect the exact input arguments and the raw JSON returned from the Microsoft Graph.

Q: How do I restrict Bing Search domains inside an OpenAI Agents SDK system?

Use the customsearch tool to bind your queries to a specific Configuration ID. This forces your OpenAI agents to stay inside your approved domain list.

Q: Can my OpenAI Agents SDK agent predict query intent?

Yes, your agent can call autosuggest to get high-velocity query completions as a user types. This lets the OpenAI Agents SDK predict search intent before executing a full web query.

Run safe, audited Bing Search queries across your OpenAI Agents SDK production nodes.

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 OpenAI Agents SDK

Create your Vinkius account to connect Bing Search to OpenAI Agents 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe OpenAI Agents SDK web queries

The `search_web` tool exposes raw web access to your multi-agent architecture. Running this on our hosted MCP Server infrastructure allows you to inspect and validate every Bing search query using OpenAI Agents SDK guardrails before execution. When an agent spots a trend using `trending_news`, it can hand off the task to a deep-dive specialist. The OpenAI Agents SDK tracing system maps the entire handoff, showing you exactly how the downstream agent used `search_news` to verify the viral story.

Structured entity resolution for agent handoffs

The `search_entities` tool lets your coordinator agent retrieve structured data on people or places. The OpenAI Agents SDK then routes this clean Bing entity context directly to a specialized writer agent. If the search results require visual assets, the agent can call `search_images` to find exact pixel dimensions. You can monitor these MCP tool calls directly on your OpenAI developer dashboard to track agent performance.

Targeted domain searches with strict guardrails

The `custom_search` tool keeps your agents focused on trusted sources. This MCP Server lets your OpenAI Agents SDK pipeline query only whitelisted domains, keeping your research agents from wandering off-topic. To keep inputs clean, run incoming user queries through `spellcheck` before triggering the search. This keeps your OpenAI Agents SDK reasoning loop tight and prevents spelling mistakes from derailing the downstream search logic.

Setup guide

Set up Bing Search MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Bing Search tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Bing Search tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Bing Search tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Bing Search Agent",
            instructions="You have access to Bing Search tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Set cacheToolsList=True in your OpenAI Agents SDK configuration to prevent constant MCP schema polling. You can also write a custom Python guardrail to throttle outgoing `search_web` calls across your agent pool.

Yes, every execution of `search_local` or `search_videos` shows up in your run traces. You can inspect the exact input arguments and the raw JSON returned from the Microsoft Graph.

Use the `custom_search` tool to bind your queries to a specific Configuration ID. This forces your OpenAI agents to stay inside your approved domain list.

Yes, your agent can call `autosuggest` to get high-velocity query completions as a user types. This lets the OpenAI Agents SDK predict search intent before executing a full web query.

Your raw search queries and IP headers are processed in an ephemeral MCP sandbox. No search history is stored, ensuring your OpenAI Agents SDK pipeline remains secure.

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