2,500+ MCP servers ready to use
Vinkius

Serper MCP Server for OpenAI Agents SDK 3 tools — connect in under 2 minutes

Built by Vinkius GDPR 3 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Serper through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.

Vinkius supports streamable HTTP and SSE.

python
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Serper Assistant",
            instructions=(
                "You help users interact with Serper. "
                "You have access to 3 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Serper"
        )
        print(result.final_output)

asyncio.run(main())
Serper
Fully ManagedVinkius Servers
60%Token savings
High SecurityEnterprise-grade
IAMAccess control
EU AI ActCompliant
DLPData protection
V8 IsolateSandboxed
Ed25519Audit chain
<40msKill switch
Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Serper MCP Server

Connect your AI agent to Serper.dev — the fastest and most cost-effective way to get Google Search results programmatically.

The OpenAI Agents SDK auto-discovers all 3 tools from Serper through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries Serper, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.

What you can do

  • Google Search — Get organic search results with titles, links, snippets, and positions. Supports geolocation and language parameters for localized results
  • Google News — Search the latest news articles with headlines, sources, publication dates, and snippets
  • Google Images — Find image results with URLs, titles, and source pages for visual research

Why Serper?

  • 2,500 free searches/month — the most generous free tier for Google SERP APIs
  • Sub-100ms latency — fastest Google SERP API available
  • Native LangChain/CrewAI integration — the default search tool for most AI frameworks

The Serper MCP Server exposes 3 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Serper to OpenAI Agents SDK via MCP

Follow these steps to integrate the Serper MCP Server with OpenAI Agents SDK.

01

Install the SDK

Run pip install openai-agents in your Python environment

02

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

03

Run the script

Save the code above and run it: python agent.py

04

Explore tools

The agent will automatically discover 3 tools from Serper

Why Use OpenAI Agents SDK with the Serper MCP Server

OpenAI Agents SDK provides unique advantages when paired with Serper through the Model Context Protocol.

01

Native MCP integration via `MCPServerSse` — pass the URL and the SDK auto-discovers all tools with full type safety

02

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

03

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

04

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Serper + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Serper MCP Server delivers measurable value.

01

Automated workflows: build agents that query Serper, process the data, and trigger follow-up actions autonomously

02

Multi-agent orchestration: create specialist agents — one queries Serper, another analyzes results, a third generates reports

03

Data enrichment pipelines: stream data through Serper tools and transform it with OpenAI models in a single async loop

04

Customer support bots: agents query Serper to resolve tickets, look up records, and update statuses without human intervention

Serper MCP Tools for OpenAI Agents SDK (3)

These 3 tools become available when you connect Serper to OpenAI Agents SDK via MCP:

01

google_image_search

dev to query Google Images and return structured results including image URLs, titles, and source pages. Useful for visual research, content creation, and reference gathering. Search Google Images for visual content related to any query. Returns image URLs, titles, and sources

02

google_news_search

dev to query Google News and return the most recent news articles matching your query. Perfect for monitoring breaking news, industry trends, and competitor announcements. Search Google News for the latest articles on any topic. Returns headlines, sources, dates, and snippets

03

google_search

dev to perform a real-time Google Search and return structured organic results. Supports geolocation (gl) and language (hl) parameters for localized results. Returns up to 100 results per query. Search Google and get organic SERP results instantly. Returns titles, links, snippets, and positions for any query

Example Prompts for Serper in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Serper immediately.

01

"Search Google for 'best AI agent frameworks 2026' and show me the top 5 results."

02

"Search the latest news about OpenAI."

03

"Search Google Images for 'neural network architecture diagram'."

Troubleshooting Serper MCP Server with OpenAI Agents SDK

Common issues when connecting Serper to OpenAI Agents SDK through the Vinkius, and how to resolve them.

01

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents
02

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Serper + OpenAI Agents SDK FAQ

Common questions about integrating Serper MCP Server with OpenAI Agents SDK.

01

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.
02

Can I use multiple MCP servers in one agent?

Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.
03

Does the SDK support streaming responses?

Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with the Vinkius.

Connect Serper to OpenAI Agents SDK

Get your token, paste the configuration, and start using 3 tools in under 2 minutes. No API key management needed.