How to Use the MongoDB Atlas Vector Search MCP in OpenAI Agents SDK

Q: How do I configure MongoDB Atlas Vector Search with the OpenAI Agents SDK?

Install the package using pip install openai-agents and initialize the server using MCPServerStreamableHttp. Pass this instance into your agent's constructor inside the mcpservers list to register the MCP Server automatically.

Q: Can OpenAI Agents SDK automatically build indexes in MongoDB Atlas Vector Search?

Yes. The agent can use the createindex tool to define and build vector indexes dynamically based on your dimension requirements.

Q: How does OpenAI Agents SDK handle search queries against MongoDB Atlas Vector Search?

The agent invokes the search tool, which executes a highly-dimensional similarity query using the $vectorSearch operator, returning the most relevant documents directly to the agent's context.

Q: What happens if my database collection is empty during an OpenAI Agents SDK search?

If the collection is empty, the search tool returns an empty list to the OpenAI Agents SDK, allowing your agent to gracefully prompt for an insert call.

Run secure, production-grade vector searches using this MCP Server inside your OpenAI Agents SDK workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MongoDB Atlas Vector Search MCP to OpenAI Agents SDK

Create your Vinkius account to connect MongoDB Atlas Vector 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 MongoDB Atlas Vector Search with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index and query vectors securely with OpenAI Agents SDK

Stop building fragile custom connectors for your vector database. This MCP Server lets your OpenAI agent build indexes on the fly using `create_index` and execute similarity queries with `search` directly through the streamable HTTP interface. The agent discovers these tools instantly, meaning you write less boilerplate and get production-ready search up and running in minutes. Because you are running a production agent, safety matters. The OpenAI Agents SDK verifies each database call before it hits MongoDB, preventing your agent from executing rogue database queries or corrupting your index configurations.

Let specialized agents manage document lifecycles

Your coordinator agent can route MongoDB Atlas Vector Search tasks to specialized sub-agents in the OpenAI Agents SDK. A data-ingestion agent handles `insert` to add raw texts and embeddings, while a maintenance agent runs `delete` when records expire. OpenAI's native handoffs ensure that the agent executing database writes is completely isolated from the agent handling public search queries. You can monitor these tool calls in real time on your OpenAI developer dashboard. If an agent tries to modify a collection that does not exist, the SDK catches the error before the query execution fails, giving you complete visibility into database interactions.

Inspect and query MongoDB Atlas without manual code

Finding specific documents or verifying index states usually requires writing custom lookup scripts. This MCP integration lets your agent inspect collection metadata using `list_collections` and retrieve specific raw documents using `find` without manual query writing. To keep latency low, configure the server with `cacheToolsList=True` during initialization. This prevents the agent from requesting the tool definitions on every turn, shaving precious milliseconds off your vector search pipeline.

Setup guide

Set up MongoDB Atlas Vector 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 MongoDB Atlas Vector Search tools at runtime.
3

Create your Agent

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

Install the package using `pip install openai-agents` and initialize the server using `MCPServerStreamableHttp`. Pass this instance into your agent's constructor inside the `mcp_servers` list to register the MCP Server automatically.

Yes. The agent can use the `create_index` tool to define and build vector indexes dynamically based on your dimension requirements.

The agent invokes the `search` tool, which executes a highly-dimensional similarity query using the `$vectorSearch` operator, returning the most relevant documents directly to the agent's context.

If the collection is empty, the `search` tool returns an empty list to the OpenAI Agents SDK, allowing your agent to gracefully prompt for an `insert` call.

Your database credentials and vector embeddings are processed within an isolated V8 sandbox on Vinkius. The server never stores your database connection strings, and all traffic between the OpenAI Agents SDK and the database is fully encrypted in transit.

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