How to Use the Vald MCP in OpenAI Agents SDK

Q: How do I search for vectors with Vald and OpenAI Agents SDK?

The searchvectors tool takes a query vector (a JSON array of floats) and executes a nearest neighbor search. It returns the most similar records stored in your index, giving your agent immediate context.

Q: What happens if I need to delete data using Vald and OpenAI Agents SDK?

You use deletevector for permanent removal. Remember, this action is irreversible; it scrubs the specified vector from the Vald index completely.

Q: Can my agent check the status of Vald using OpenAI Agents SDK?

Yep. Running getengineinfo gives you all the operational details and health information about the Vald engine, letting you confirm it's running right.

Build production agents that query and manage dense vectors using OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Vald MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search for Nearest Vectors with the MCP Server

The `search_vectors` tool performs a nearest neighbor vector similarity search. You give it a query vector as a JSON array of floats, and Vald returns the closest matches from your index. This means your agent can find related information instantly, making context-aware decisions without needing complex relational lookups.

Manage Vector Data with OpenAI Agents SDK

Use `insert_vector` to put new data into the Vald index. Just provide a unique ID and your vector as a JSON array. The system handles the indexing, keeping your knowledge base current. Need an update? Use `update_vector`. You just pass the existing ID and the new vector data; it overwrites the old entry cleanly.

Maintain Vald Index Health

You can check the operational status with `get_engine_info`, which retrieves detailed health metrics for the Vald engine. It's good practice to run this before deploying anything major. Want to see what data is stored? The `get_vector_details` tool lets you retrieve the raw vector data using a specific ID, so you can verify exactly what's in the database.

Setup guide

Set up Vald 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 Vald tools at runtime.
3

Create your Agent

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

Run the agent

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

The `search_vectors` tool takes a query vector (a JSON array of floats) and executes a nearest neighbor search. It returns the most similar records stored in your index, giving your agent immediate context.

You use `delete_vector` for permanent removal. Remember, this action is irreversible; it scrubs the specified vector from the Vald index completely.

Yep. Running `get_engine_info` gives you all the operational details and health information about the Vald engine, letting you confirm it's running right.

This server handles dense vectors—those JSON arrays of floats. You interact with these vectors using IDs to insert, update, or retrieve their raw data.

The MCP Server manages the storage and retrieval of the dense vector data. You control what gets inserted via `insert_vector` and what gets searched for using specific IDs.

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