How to Use the ClickHouse (Vector Search) MCP in OpenAI Agents SDK

Q: How do I connect this ClickHouse (Vector Search) MCP Server to my OpenAI Agents SDK pipeline?

Install the package using pip, then initialize the MCPServerStreamableHttp client with your Vinkius endpoint. Pass the server instance inside the mcpservers list when instantiating your Agent.

Q: Can my agents write data back using this database setup?

Yes. The executesql tool runs arbitrary DML and DDL statements. This allows your agent to insert new vector records or alter tables if you grant those permissions.

Run high-speed vector queries against ClickHouse directly from your OpenAI Agents SDK workflows using this secure MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ClickHouse (Vector Search) MCP to OpenAI Agents SDK

Create your Vinkius account to connect ClickHouse (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 ClickHouse (Vector Search) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fast vector search with OpenAI Agents SDK

The `vector_search` tool sends high-dimensional embeddings straight to your cluster to find nearest neighbors in milliseconds. Your agent triggers this math-heavy operation during live conversations, bypassing slow middleware. By calling `execute_sql` alongside your search, the agent can immediately join those vector results with metadata tables. This lets your production system run complex filtering without manual python-side data stitching. This MCP integration handles the heavy lifting.

Schema discovery and cluster inspection

The `describe_table` tool extracts column definitions and active schemas so your agent knows exactly which fields to query. This prevents syntax errors before the agent even drafts an SQL command. To keep tabs on production performance, the agent uses `get_table_stats` and `get_version` to check cluster health and HNSW index support. This ensures your agent dynamically adapts its query patterns based on what the database actually supports.

Database mapping for autonomous routing

The `list_databases` tool maps out all top-level schemas available to the connection. Your agent uses this map to decide which database holds the relevant vector tables for a user's prompt. Once the target database is selected, `list_tables` verifies the specific table limits and structures inside it. This two-step discovery prevents your agent from hallucinating table names or querying non-existent datasets.

Setup guide

Set up ClickHouse (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 ClickHouse (Vector Search) tools at runtime.
3

Create your Agent

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

Install the package using pip, then initialize the `MCPServerStreamableHttp` client with your Vinkius endpoint. Pass the server instance inside the `mcp_servers` list when instantiating your Agent.

Yes. The `execute_sql` tool runs arbitrary DML and DDL statements. This allows your agent to insert new vector records or alter tables if you grant those permissions.

The SDK automatically discovers all seven tools when you boot the agent. Set `cacheToolsList=True` in your configuration to avoid fetching the tool definitions on every single request.

Yes. You can filter the tools list before passing it to the Agent constructor. This keeps your agent focused on search rather than schema modifications.

All vector embeddings and SQL queries run through this MCP Server inside a secure, isolated V8 sandbox hosted by Vinkius. Your database credentials never expose themselves to the client, and connection tokens remain ephemeral.

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