How to Use the Vertex AI Search MCP in OpenAI Agents SDK

Q: How does Vertex AI Search integrate with the OpenAI Agents SDK?

The openai-agents-sdk auto-discovers the MCP tools from your Vertex AI Search server. You just pass the endpoint, and the agents see all available functions like searchdocuments. This keeps your setup clean.

Q: Can I list all my indexes using Vertex AI Search and the OpenAI Agents SDK?

Yes. You can call listsearchengines to see every search engine configured in your collection. This helps confirm that all necessary data stores are pointed at the correct services.

Q: Does Vertex AI Search handle document listing with OpenAI Agents SDK?

Absolutely. To check what's indexed, you can use listdatastoredocuments. You only need to provide the data store ID and branch IDs for this function call.

Grounding Answers with OpenAI Agents SDK: Connect your agents directly to private data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Vertex AI Search MCP to OpenAI Agents SDK

Create your Vinkius account to connect Vertex AI 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 Vertex AI Search with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get answers grounded in internal docs.

Need an answer based on proprietary documents? The `get_grounded_answer` tool handles that. Your agent calls this, and it returns a natural language response using your private data as the source. It's perfect for building agents that need to cite sources from internal manuals or knowledge bases.

Search across all enterprise documents.

The `search_documents` tool lets you run a query against an entire data store. You pass the necessary data store ID and your search text, and it executes the semantic search. This is how your agent performs deep research on company docs without needing to manually build complex retrieval pipelines.

Find recommendations based on user actions.

If you want personalized results, use `get_recommendations`. This tool requires two inputs: the data store ID and a JSON object containing user event data. The system then pulls together relevant suggestions. Agents can automatically pass real-time user behavior to this function, making recommendations actionable right away.

Setup guide

Set up Vertex AI 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 Vertex AI Search tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Vertex AI 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 Vertex AI 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="Vertex AI Search Agent",
            instructions="You have access to Vertex AI 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 Vertex AI 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 Vertex AI 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 Vertex AI Search MCP in OpenAI Agents SDK

The `openai-agents-sdk` auto-discovers the MCP tools from your Vertex AI Search server. You just pass the endpoint, and the agents see all available functions like `search_documents`. This keeps your setup clean.

This MCP Server touches configuration metadata for data stores. Specifically, it deals with structured information retrieved by tools such as `get_datastore_details` and general search query text.

Yes. You can call `list_search_engines` to see every search engine configured in your collection. This helps confirm that all necessary data stores are pointed at the correct services.

Absolutely. To check what's indexed, you can use `list_datastore_documents`. You only need to provide the data store ID and branch IDs for this function call.

The server operates on private documents within designated data stores. The tool primarily reads document content and metadata, never exposing the raw source files outside of the defined search context.

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