How to Use the MyScale (SQL Vector Database API) MCP in OpenAI Agents SDK

Q: How do I perform a search in MyScale (SQL Vector Database API) using OpenAI Agents SDK?

Use the vectorsearch tool within your agent's toolset. It handles the SQL construction so you only pass the query vector and table name.

Q: Can OpenAI Agents SDK monitor index builds on MyScale (SQL Vector Database API)?

Yes. You'll call checkindexstatus to poll the index state. It returns the current status, so you can wait until it hits the 'Built' state.

Q: How do I check if my connection to the database is live?

Call pingcluster from your agent code. It returns a simple status, confirming your agent can reach the database host.

Run SQL-based vector searches directly from your OpenAI Agents SDK production pipeline.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MyScale (SQL Vector Database API) MCP to OpenAI Agents SDK

Create your Vinkius account to connect MyScale (SQL Vector Database API) 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 MyScale (SQL Vector Database API) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Full SQL control for your OpenAI Agents SDK

Stop wrestling with custom vector APIs and just write SQL. Use `execute_sql_query` to pull data directly into your agent's context, letting you handle both relational and vector data in one go. You'll get consistent results because your agent runs standard statements. It's the cleanest way to move data from the database to your production application without middle-tier bloat.

Manage vector indices via OpenAI Agents SDK

Building indexes shouldn't be a black box. Your agent can trigger `create_vector_index` and then monitor the progress with `check_index_status` to ensure your data is ready for production traffic. Catch errors before they hit your users. By checking the index state programmatically, your agent knows exactly when it can safely perform similarity searches.

Run similarity searches using OpenAI Agents SDK

Skip the complex query constructors. Call `vector_search` to find relevant embeddings and let the database return the exact matches your agent needs to answer questions. This tool abstracts the distance calculations. Your agent focuses on the logic while this MCP server handles the heavy lifting of finding the closest vectors in your MyScale tables.

Setup guide

Set up MyScale (SQL Vector Database API) 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 MyScale (SQL Vector Database API) tools at runtime.
3

Create your Agent

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

Run the agent

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

Use the `vector_search` tool within your agent's toolset. It handles the SQL construction so you only pass the query vector and table name.

Yes. You'll call `check_index_status` to poll the index state. It returns the current status, so you can wait until it hits the 'Built' state.

Absolutely. Since the server exposes structured tools, the SDK validates your inputs before the request reaches the database.

Call `ping_cluster` from your agent code. It returns a simple status, confirming your agent can reach the database host.

Your data stays in your MyScale cluster. The MCP server only acts as a bridge for SQL commands, ensuring no raw data is cached by the agent itself.

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

Mastra AI sdk-typescript

Start using the MyScale (SQL Vector Database API) MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Get started