How to Use the Weaviate MCP in OpenAI Agents SDK

Q: How do I use Weaviate and the OpenAI Agents SDK to find related documents?

You call the searchnearvector tool. Your agent sends a query vector, along with the required class name, and Weaviate returns the top matching objects based on similarity.

Q: Does the OpenAI Agents SDK handle schema changes in Weaviate?

Yes. You can use getfullschema to pull the complete definitions of all collections, giving your agent up-to-date knowledge of the entire data structure.

Q: What kind of metadata does the OpenAI Agents SDK get from Weaviate?

The getinstancemetadata tool pulls operational details about the entire Weaviate instance. This is useful for agents that need to check connectivity or deployment context.

Q: Can I list objects in Weaviate using the OpenAI Agents SDK?

Absolutely. The listobjects tool supports basic pagination, so you can iterate through records within a specific class without hitting API limits.

Build reliable AI applications with the OpenAI Agents SDK and Weaviate's vector search.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Weaviate MCP to OpenAI Agents SDK

Create your Vinkius account to connect Weaviate 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 Weaviate with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Vector Similarity Search

The `search_near_vector` tool lets your agent find related data. You just provide a class name and a query vector array, and it returns the closest neighbors in Weaviate. This mechanism means your deployed product doesn't guess; it retrieves contextually relevant information for the user.

Schema Discovery

Need to know what data structure you're dealing with? The `get_full_schema` tool pulls up every collection definition in Weaviate. This lets your agent build internal logic before attempting any reads. It also runs `get_class_schema`, which gives you the specific definitions for a single class, helping your agent validate expected input types.

Data Object Retrieval

When an agent gets a UUID from another source, it doesn't have to guess what data is attached. Calling `get_object_details` fetches all metadata about that specific object instantly. Plus, you can list records using `list_objects`, supporting basic pagination with the limit parameter for bulk checks.

Setup guide

Set up Weaviate 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 Weaviate tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Weaviate tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Weaviate 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="Weaviate Agent",
            instructions="You have access to Weaviate 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 Weaviate. 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 Weaviate 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 Weaviate MCP in OpenAI Agents SDK

You call the `search_near_vector` tool. Your agent sends a query vector, along with the required class name, and Weaviate returns the top matching objects based on similarity.

Yes. You can use `get_full_schema` to pull the complete definitions of all collections, giving your agent up-to-date knowledge of the entire data structure.

The `get_instance_metadata` tool pulls operational details about the entire Weaviate instance. This is useful for agents that need to check connectivity or deployment context.

Absolutely. The `list_objects` tool supports basic pagination, so you can iterate through records within a specific class without hitting API limits.

This server touches object UUIDs and vector float arrays. These are the primary identifiers and context inputs used when calling `get_object_details` or `search_near_vector`.

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