How to Use the Bing Search MCP in Pydantic AI

Bring Bing Search into Pydantic AI with strict type validation for every web result your agent receives.

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 Pydantic AI

Create your Vinkius account to connect Bing Search to Pydantic 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Typed web search for Pydantic AI

Pass `search_web` results through your Pydantic models to ensure every snippet is structured correctly. If the web data doesn't match your schema, the agent catches the error immediately. This stops your agent from hallucinating fields or processing malformed search output. You define the shape of the data and the server fills it.

Validated media and news with Bing Search

Use `search_news` and `search_images` to bring external content into your agent's type-safe environment. You validate the response structure before the agent acts on it. `get_trending_news` lets you monitor the web for updates. Your Pydantic AI agent processes these news items as validated objects, keeping your logic sound.

Precise local and video queries

Query `search_local` for business data that conforms to your strict Python types. Your agent avoids type-mismatch errors during runtime. `search_suggestions` provides extra input for your search logic. Pydantic AI ensures that all suggestions received from the server are valid before your agent uses them.

Setup guide

Set up Bing Search MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "bing-search-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Bing Search tools.",
)

result = await agent.run("List recent Bing Search transactions")
print(result.output)

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 Pydantic AI

Each tool response is validated against your defined Pydantic models. If the server returns bad data, the agent triggers a validation error instead of crashing later.

Yes, the MCP Server is model-agnostic. You can pair it with whichever model your Pydantic AI agent is using for its current task.

It does. You can configure your MCPToolset to connect via SSE, ensuring a persistent and reliable link for your server-side agent.

Install the slim MCP package and initialize the MCPToolset with your Vinkius endpoint. Then, pass that toolset directly to your agent instance.

Your queries are treated as transient memory in an ephemeral sandbox. The server holds no state, and your search keywords are wiped the moment the task completes.

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