How to Use the Basis Technologies MCP in OpenAI Agents SDK

Q: Can OpenAI Agents SDK read Basis Technologies campaign performance?

Yes, the agent calls getcampaignperformance directly. The framework's built-in guardrails ensure the agent requests the correct metric windows before executing the tool.

Q: What is the best way to list ads across multiple brands?

Instruct your agent to run listbrands first. It then iterates through those IDs using listads to pull the creative catalog for each brand.

Connect OpenAI Agents SDK to Basis DSP. Build production agents that manage campaigns and read ad performance with full trace logging.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Basis Technologies MCP to OpenAI Agents SDK

Create your Vinkius account to connect Basis Technologies 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 Basis Technologies with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Read Basis DSP Campaigns via MCP Server

Your OpenAI agent uses `list_campaigns` and `get_campaign` to inspect active media buys. The SDK auto-discovers these endpoints when you pass the Vinkius URL to the Agent constructor. Agents pull budget pacing and flight dates without custom API wrappers. Guardrails built into the framework validate the agent's actions before it fetches data. Handoffs let a specialized reporting agent call `get_campaign_performance` while a separate creative agent handles the ads. Tracing in the OpenAI dashboard logs every HTTP request made to the DSP.

Inspect Tactics and Line Items

Fetching specific targeting details happens through the `get_tactic` and `list_tactics` tools. Your agent maps these line items to the parent campaign. Performance data flows back into your Python application via `get_tactic_performance`. Setting `cacheToolsList=True` prevents the agent from re-fetching the tool schema on every run. Production deployments benefit from this reduced latency. You get faster response times when querying complex programmatic setups across multiple advertisers.

Map Clients to Ad Creatives

Auditing an advertiser's account starts with `list_clients` and `list_brands`. The agent groups the hierarchy before calling `list_ads` to see the actual creatives. Specific creative metadata comes back through `get_ad`. You run this through the `async with` context manager using `MCPServerStreamableHttp`. The connection remains open while the agent correlates brand metrics with ad performance. No manual authentication headers are required since Vinkius handles the endpoint token.

Setup guide

Set up Basis Technologies 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 Basis Technologies tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the openai-agents package via pip. Create an MCPServerStreamableHttp instance with your Vinkius endpoint. Pass that into your agent's mcp_servers list to auto-discover the DSP tools.

Yes, the agent calls get_campaign_performance directly. The framework's built-in guardrails ensure the agent requests the correct metric windows before executing the tool.

You can build a system where one agent fetches brands via list_brands and hands off the ID to a reporting agent. That second agent then runs get_tactic_performance to analyze the specific line items.

Instruct your agent to run list_brands first. It then iterates through those IDs using list_ads to pull the creative catalog for each brand.

Campaign budgets and ad performance metrics run through the Vinkius V8 Isolate Sandbox. The execution environment is completely ephemeral and tears down immediately after your agent finishes querying the DSP.

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