How to Use the CockroachDB Cloud MCP in OpenAI Agents SDK

Q: How do I connect my CockroachDB Cloud clusters to the OpenAI Agents SDK?

Install openai-agents and initialize the MCPServerStreamableHttp client with your Vinkius MCP endpoint. Pass this server instance inside the mcpservers list when instantiating your agent. The SDK auto-discovers all eight database management tools immediately.

Q: Does the OpenAI Agents SDK handle multi-region CockroachDB Cloud setups?

Absolutely. When your agent calls getclusterclouddetails, it receives the complete regional configuration of your distributed database. The agent parses this payload to identify node distribution across AWS or GCP regions.

Q: How is my CockroachDB Cloud network allowlist data secured?

All cluster metadata, including IP allowlists retrieved by listnetworkallowlist, stays locked inside your ephemeral Vinkius sandbox. Your database credentials never touch OpenAI's training servers. We run every request in isolated V8 sandboxes that self-destruct immediately after execution.

Control your CockroachDB Cloud clusters directly from production OpenAI Agents SDK setups without writing manual API glue.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CockroachDB Cloud MCP to OpenAI Agents SDK

Create your Vinkius account to connect CockroachDB Cloud 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 CockroachDB Cloud with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit cluster health with OpenAI Agents SDK

Your production agent needs to know what's happening with your database. By hooking this MCP server up, your agent calls `list_cockroach_clusters` and `list_cluster_nodes` to inspect live cluster topologies. It gets raw node health metrics without you writing custom API routes. This setup lets you build autonomous ops agents that spot dead nodes instantly. The SDK handles tool discovery automatically, giving your agent direct visibility into multi-region deployments.

Track running operations and scaling events

Stop guessing if a cluster resize finished. Your agent uses `list_cluster_operations` to monitor ongoing schema updates, scaling actions, or version upgrades. Because the OpenAI Agents SDK supports strict guardrails, you can safely let your agent watch these background tasks. It checks `get_cluster_cloud_details` to verify the exact state before letting downstream workflows proceed.

Inspect network rules and encryption keys

Security audits shouldn't require clicking around a web console. Your agent polls `list_network_allowlist` and `list_encryption_keys` to verify your database perimeter is tight. If a key is missing or an IP rule looks sketchy, the agent flags it. The OpenAI dashboard traces these MCP tool calls, so you see exactly when and why the agent inspected your security configuration.

Setup guide

Set up CockroachDB Cloud 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 CockroachDB Cloud tools at runtime.
3

Create your Agent

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

Run the agent

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

Install `openai-agents` and initialize the `MCPServerStreamableHttp` client with your Vinkius MCP endpoint. Pass this server instance inside the `mcp_servers` list when instantiating your agent. The SDK auto-discovers all eight database management tools immediately.

Yes, you control this by configuring the agent's tool access policies or using specialized agent handoffs. For safety, set `cacheToolsList=True` to keep tool definitions stable across runs. This keeps your MCP Server integrations predictable.

Absolutely. When your agent calls `get_cluster_cloud_details`, it receives the complete regional configuration of your distributed database. The agent parses this payload to identify node distribution across AWS or GCP regions.

Use the OpenAI developer dashboard to trace every tool call. You will see the exact inputs passed to `list_cluster_operations` and the raw JSON payload returned by the database API.

All cluster metadata, including IP allowlists retrieved by `list_network_allowlist`, stays locked inside your ephemeral Vinkius sandbox. Your database credentials never touch OpenAI's training servers. We run every request in isolated V8 sandboxes that self-destruct immediately after execution.

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