How to Use the AdButler MCP in OpenAI Agents SDK

Q: How do I connect the AdButler MCP Server to my OpenAI Agents SDK pipeline?

Install openai-agents and initialize MCPServerStreamableHttp pointing to your Vinkius endpoint. Pass this server instance in the mcpservers list when creating your Agent.

Q: How does the OpenAI Agents SDK handle high-volume getstats requests from AdButler?

Enable cacheToolsList=True in your SDK configuration to prevent redundant tool schema lookups. This keeps your agent fast when pulling large batches of impression and click data.

Q: What happens if the AdButler API goes down mid-run?

The checkadbutlerstatus tool returns an error state, which your agent catches. The SDK then routes the failure through your standard error-handling paths instead of crashing the process.

Run production-ready ad operations agents with the OpenAI Agents SDK and live AdButler data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AdButler MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate AdButler Campaign Status via OpenAI Agents SDK

The `check_adbutler_status` tool verifies your connection to the ad server before your OpenAI agent triggers any campaign modifications. This step stops broken API requests from hitting your live ad server, saving you from failed runs in production. By calling `list_campaigns` and `get_campaign` through this MCP Server, your OpenAI agent pulls active flight dates and budget caps directly into its context. The OpenAI Agents SDK then validates these parameters against your custom safety guardrails before executing any optimization steps.

Run Multi-Agent Ad Allocation Pipelines

The `list_zones` tool exposes your physical and digital ad zones so specialized OpenAI agents can target placements with high-performing banners. One agent can analyze performance using `get_stats` while another coordinates with the publisher side of your network. This MCP Server lets you hand off tasks between a publisher agent using `list_publishers` and an advertiser agent running `list_advertisers` inside the OpenAI SDK. The OpenAI tracing dashboard logs each tool call, giving you a clear audit trail of how your budget shifts across zones.

Fetch Performance Metrics for Live Advertisers

The `get_stats` tool pulls impression, click, and conversion metrics directly into your OpenAI agent's reasoning loop. Your agent reads raw numbers instead of guessing performance trends. Combining `get_advertiser` with `list_banners` lets your OpenAI agent spot underperforming creatives in real time. You can cache these tool definitions in the SDK to keep agent response times under a second.

Setup guide

Set up AdButler 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 AdButler tools at runtime.
3

Create your Agent

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

Run the agent

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

Install `openai-agents` and initialize `MCPServerStreamableHttp` pointing to your Vinkius endpoint. Pass this server instance in the `mcp_servers` list when creating your Agent.

Yes. You can restrict the agent's tools list during initialization or use the SDK's built-in guardrails to block write actions while allowing you to specify which MCP tools are exposed.

Enable `cacheToolsList=True` in your SDK configuration to prevent redundant tool schema lookups. This keeps your agent fast when pulling large batches of impression and click data.

The `check_adbutler_status` tool returns an error state, which your agent catches. The SDK then routes the failure through your standard error-handling paths instead of crashing the process.

All requests run inside an ephemeral V8 sandbox that destroys itself after execution. Your AdButler API tokens never persist on disk, and the server only touches the specific advertiser details and campaign statistics your OpenAI agent requests.

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