How to Use the DoiT MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK setup automatically check if we exceeded our budgets using DoiT?

Yes, your agent uses listexceededcostbudgets to fetch any active budgets that have crossed their limits. This allows the agent to run automated checks during routine Slack reports or CI/CD pipelines.

Q: How does DoiT handle multi-cloud accounts in OpenAI Agents SDK?

The server uses listconnectedcloudaccounts to identify all AWS, GCP, and Azure accounts linked to your organization. Your agent can query this list to map costs back to specific clouds dynamically.

Q: What is the best way to get metadata for my organization?

Your agent calls getdoitaccountmetadata to retrieve your organization's specific details. This ensures your agent is executing commands under the correct billing entity.

Give your OpenAI Agents SDK production agents direct access to cloud cost metrics and anomaly tracking via the DoiT 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 DoiT MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track cloud spend directly inside OpenAI Agents SDK

This MCP Server exposes `get_billing_cost_summary` to give your agent a high-level view of your multi-cloud spending. It pulls raw financial metrics directly from AWS, GCP, and Azure without requiring custom API glue code. Your python agents use these numbers to run automatic budget checks. They can trigger handoffs to specialized billing agents when spending spikes, keeping your production deployment safe from runaway cloud bills.

Detect real-time cost spikes with OpenAI Agents SDK

The `list_critical_cost_spikes` tool lets your agent scan for major, unexpected jumps in cloud spending across your entire infrastructure. It isolates high-severity anomalies so your agent can alert the engineering team before the next billing cycle. By combining this with `list_cost_anomalies`, your agent monitors daily fluctuations and flags weird patterns. You get proactive guardrails that catch misconfigured loops or runaway test environments on the fly.

Inspect specific cloud assets with OpenAI Agents SDK

The `search_cloud_assets` tool allows your agent to find specific cloud resources using simple keyword queries. It returns matches across all your connected cloud providers instantly. Once found, the agent calls `get_asset_details` to pull configuration and cost metadata for that specific asset. This gives your agent the exact context needed to pinpoint which database or VM is driving up your bills.

Setup guide

Set up DoiT 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 DoiT tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package, then initialize the streamable HTTP server pointing to your Vinkius endpoint. Pass this instance directly into your Agent constructor's server list to enable automatic tool discovery.

Yes, your agent uses `list_exceeded_cost_budgets` to fetch any active budgets that have crossed their limits. This allows the agent to run automated checks during routine Slack reports or CI/CD pipelines.

The server uses `list_connected_cloud_accounts` to identify all AWS, GCP, and Azure accounts linked to your organization. Your agent can query this list to map costs back to specific clouds dynamically.

Your agent calls `get_doit_account_metadata` to retrieve your organization's specific details. This ensures your agent is executing commands under the correct billing entity.

Vinkius runs the server in an isolated V8 sandbox, ensuring your API keys never leak. Your cloud billing and asset data is processed in ephemeral memory and is never stored or logged on our servers.

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