How to Use the Marqo AI (Vector Search & Embeddings) MCP in OpenAI Agents SDK

Q: How do I connect Marqo AI (Vector Search & Embeddings) to the OpenAI Agents SDK?

Install the openai-agents package. Create an MCPServerStreamableHttp object with your endpoint URL and pass it to the mcpservers list in your Agent constructor.

Q: Can the agent create new Marqo AI (Vector Search & Embeddings) indexes automatically in OpenAI Agents SDK?

Yes. The agent uses the createindex tool to spin up explicitly bounded vector spaces. You can set guardrails in the SDK to require human approval before this happens.

Q: Does the agent know which indexes exist before searching?

It should. You instruct the agent to run listindexes first. This prevents it from guessing collection names and failing on the search step.

Build production-ready semantic search workflows with OpenAI Agents SDK and Marqo AI vector embeddings.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Marqo AI (Vector Search & Embeddings) MCP to OpenAI Agents SDK

Create your Vinkius account to connect Marqo AI (Vector Search & Embeddings) 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 Marqo AI (Vector Search & Embeddings) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Vector Search within OpenAI Agents SDK

Your agent needs to find exact conceptual matches across massive product catalogs. Using `tensor_search`, the model runs natural language queries directly against Marqo. You don't have to build custom retrieval pipelines. The agent simply takes user intent, forms a query, and grabs the highest-scoring vector matches. Setup is trivial. You pass this MCP Server into the Agent constructor using `MCPServerStreamableHttp`. The OpenAI dashboard traces every single search payload, so you know exactly what your agent asked the index in production.

Index Management & Safety

Creating and populating vector spaces happens right inside your workflow. Your agent can spin up a dedicated space using `create_index`, then push JSON payloads straight into it with `add_documents`. Since OpenAI Agents SDK uses strict guardrails, you can validate the exact structure of the documents before the agent writes them. If data gets stale, the agent prunes it. It calls `delete_documents` to drop outdated IDs. You keep the vector space clean without leaving the Python environment.

Audit Your Vector Infrastructure

Blindly querying arbitrary collections is a recipe for hallucinations. Smart agents check the environment first. By running `list_indexes`, the agent maps out available spaces before attempting a search. Monitoring performance is just as easy. The `get_index_stats` tool pulls exact document counts and index configurations. You get real-time visibility into the vector database state right before executing heavy queries.

Setup guide

Set up Marqo AI (Vector Search & Embeddings) 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 Marqo AI (Vector Search & Embeddings) tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Marqo AI (Vector Search & Embeddings) 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="Marqo AI (Vector Search & Embeddings) Agent",
            instructions="You have access to Marqo AI (Vector Search & Embeddings) 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 Marqo AI. 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 Marqo AI (Vector Search & Embeddings) 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 Marqo AI (Vector Search & Embeddings) MCP in OpenAI Agents SDK

Install the `openai-agents` package. Create an `MCPServerStreamableHttp` object with your endpoint URL and pass it to the `mcp_servers` list in your Agent constructor.

Yes. The agent uses the `create_index` tool to spin up explicitly bounded vector spaces. You can set guardrails in the SDK to require human approval before this happens.

The SDK catches the error and logs it in the OpenAI dashboard. Your agent can then attempt a fallback query or alert the user that the index is unreachable.

It should. You instruct the agent to run `list_indexes` first. This prevents it from guessing collection names and failing on the search step.

It processes raw JSON documents and vector embeddings. The V8 Isolate Sandbox ensures that when your agent pushes catalog data via `add_documents`, the memory is wiped immediately after the request finishes. No data persists in the middle layer.

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