Vertex AI Search MCP Server for OpenAI Agents SDK 7 tools — connect in under 2 minutes
The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Vertex AI Search through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
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="Vertex AI Search Assistant",
instructions=(
"You help users interact with Vertex AI Search. "
"You have access to 7 tools."
),
mcp_servers=[mcp_server],
)
result = await Runner.run(
agent, "List all available tools from Vertex AI Search"
)
print(result.final_output)
asyncio.run(main())
* 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 Vertex AI Search MCP Server
Connect your Vertex AI Search account to any AI agent and harness the power of Google's semantic search technology on your own enterprise data through natural conversation.
The OpenAI Agents SDK auto-discovers all 7 tools from Vertex AI Search through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries Vertex AI Search, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.
What you can do
- Semantic Search — Perform high-quality semantic searches across documents with AI-powered relevance and accuracy
- Grounded Answers — Get direct, natural language answers grounded in your private document collection for reliable Q&A
- Data Stores — List and browse your enterprise data stores and search engines to manage your searchable datasets
- Document Discovery — Browse and list indexed documents within your data store branches directly from your agent
- Personalized Recommendations — Retrieve intelligent recommendations based on user interaction events and patterns
- Search Engines — View and manage high-level search applications configured for specific business use cases
The Vertex AI Search MCP Server exposes 7 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 Vertex AI Search to OpenAI Agents SDK via MCP
Follow these steps to integrate the Vertex AI Search MCP Server with OpenAI Agents SDK.
Install the SDK
Run pip install openai-agents in your Python environment
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com
Run the script
Save the code above and run it: python agent.py
Explore tools
The agent will automatically discover 7 tools from Vertex AI Search
Why Use OpenAI Agents SDK with the Vertex AI Search MCP Server
OpenAI Agents SDK provides unique advantages when paired with Vertex AI Search through the Model Context Protocol.
Native MCP integration via `MCPServerSse` — pass the URL and the SDK auto-discovers all tools with full type safety
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
Vertex AI Search + OpenAI Agents SDK Use Cases
Practical scenarios where OpenAI Agents SDK combined with the Vertex AI Search MCP Server delivers measurable value.
Automated workflows: build agents that query Vertex AI Search, process the data, and trigger follow-up actions autonomously
Multi-agent orchestration: create specialist agents — one queries Vertex AI Search, another analyzes results, a third generates reports
Data enrichment pipelines: stream data through Vertex AI Search tools and transform it with OpenAI models in a single async loop
Customer support bots: agents query Vertex AI Search to resolve tickets, look up records, and update statuses without human intervention
Vertex AI Search MCP Tools for OpenAI Agents SDK (7)
These 7 tools become available when you connect Vertex AI Search to OpenAI Agents SDK via MCP:
get_datastore_details
Retrieves configuration and metadata for a specific data store
get_grounded_answer
Returns a natural language response based on your private data. Retrieves an AI-generated answer grounded in the documents of a data store
get_recommendations
Provide a data store ID and user event data as a JSON object. Retrieves personalized recommendations based on user events
list_data_stores
Lists all data stores in the Vertex AI Search collection
list_datastore_documents
Provide data store and branch IDs. Lists all indexed documents within a specific data store branch
list_search_engines
Lists all search engines configured in the collection
search_documents
Provide a data store ID and the query text. Performs a search query across documents in a specific data store
Example Prompts for Vertex AI Search in OpenAI Agents SDK
Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Vertex AI Search immediately.
"List all my available data stores in Vertex AI Search."
"Based on our documentation, what is our remote work policy?"
"Search the product catalog for 'blue wireless headphones'."
Troubleshooting Vertex AI Search MCP Server with OpenAI Agents SDK
Common issues when connecting Vertex AI Search to OpenAI Agents SDK through the Vinkius, and how to resolve them.
MCPServerStreamableHttp not found
pip install --upgrade openai-agentsAgent not calling tools
Vertex AI Search + OpenAI Agents SDK FAQ
Common questions about integrating Vertex AI Search MCP Server with OpenAI Agents SDK.
How does the OpenAI Agents SDK connect to MCP?
MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.Can I use multiple MCP servers in one agent?
MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.Does the SDK support streaming responses?
Connect Vertex AI Search with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Vertex AI Search to OpenAI Agents SDK
Get your token, paste the configuration, and start using 7 tools in under 2 minutes. No API key management needed.