How to Use the Adikteev MCP in OpenAI Agents SDK

Build production retargeting pipelines with the OpenAI Agents SDK by giving your agents direct access to Adikteev campaign data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Adikteev MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Adikteev server for OpenAI Agents

Connecting the `get_churn_scores` tool to your OpenAI Agents SDK setup lets your agent pull exact risk metrics for specific user groups. It evaluates these scores against your safety constraints before deciding if an intervention is necessary. Once the agent identifies a high-risk group, it triggers `create_segment` to push those IDs straight into a new retargeting audience. You get a full trace in your OpenAI dashboard showing exactly why the system decided to isolate that specific cohort.

Campaign reporting with guardrails

Your Python agent uses `get_reporting` to pull spend, impressions, and conversion data directly from the Adikteev platform. Since you define strict execution rules in the SDK, the agent only extracts data for the specific campaigns you explicitly authorize. It then formats this raw performance data into a structured summary for your marketing team. If the agent needs context on which company account it's querying, it runs `list_companies` first to validate the workspace ID.

Autonomous audience management

Assigning the `list_segments` tool lets your specialized audience-manager agent audit every active group in your account. It reviews the size and status of each list without requiring manual dashboard logins or CSV exports. You can configure handoffs between agents to handle complex logic. One agent analyzes the existing segments, and if it spots a gap in your retargeting strategy, it passes execution to a creator agent that spins up a new list to fill that void.

Setup guide

Set up Adikteev 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 Adikteev tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the openai-agents package via pip. Initialize MCPServerStreamableHttp with your Vinkius endpoint URL and pass it to your Agent constructor in the mcp_servers list. The SDK automatically discovers all five available tools.

Yes. Set cacheToolsList=True when configuring your MCP Server setup. This stops the agent from refetching the schema for reporting tools on every single run, which cuts down latency.

The OpenAI Agents SDK relies on your predefined guardrails. Before the agent executes segment creation, the framework validates the parameters against your rules to ensure it doesn't target the wrong user base.

Your agent handles this automatically. It calls the company listing tool to fetch your active workspace ID, then caches that value for subsequent API calls.

The Vinkius runtime isolates your session inside an ephemeral V8 sandbox. When your agent pulls user churn scores or ad performance metrics, the memory state is destroyed the second the task finishes. No data persists on the host machine.

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