How to Use the Kevel MCP in OpenAI Agents SDK

Configure OpenAI Agents SDK to audit live ad flights and pull campaign data directly through the Kevel MCP Server without manual code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kevel MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate campaign audits with OpenAI Agents SDK

The Kevel MCP Server uses `list_campaigns` and `list_flights` to expose campaign and flight data directly to your agent workflows. Your agent runs these queries to inspect active inventory setups without you writing custom API wrappers. You get instant visibility into what is running. The agent pulls live configurations through the streamable HTTP transport, letting you verify flight parameters against your internal spreadsheets.

Verify advertiser setups using built-in guardrails

This toolset uses `list_advertisers` and `get_advertiser` to let your OpenAI Agents SDK verify client accounts before pushing updates. The agent calls these tools to check matches, then pulls deep metadata to ensure nothing is misconfigured. You set the safety parameters in Python. Because the SDK enforces strict action validation, your agent never acts on hallucinated advertiser IDs or incorrect account mappings.

Map ad inventory placements dynamically

Your agent uses `list_sites` and `list_zones` to inspect your ad server structure and find where creatives can actually run. It matches this layout against your active assets using `list_creatives` to confirm compatibility. The agent handles the structural lookup in the background. It analyzes the channels returned by `list_channels` to make sure your media team is targeting the correct inventory buckets.

Setup guide

Set up Kevel 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 Kevel tools at runtime.
3

Create your Agent

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

Run the agent

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

The SDK auto-discovers all eleven tools when you register the server. You pass the Vinkius HTTP endpoint to MCPServerStreamableHttp and your agent instantly knows how to call `list_campaigns` or `list_flights`.

Yes, you control this at the agent constructor level. You can filter the tools list before passing it to your OpenAI Agents SDK, keeping sensitive tools like `list_advertisers` restricted to specific agent roles.

Turn on cacheToolsList in your SDK configuration to prevent redundant schema lookups. Since this MCP Server is read-only, you avoid write-collision risks, but you should still monitor sequential loops over `list_ads` to stay within Kevel API limits.

Assign one agent to inventory lookup and another to creative matching. The first agent uses `list_zones` to find open slots, then hands off the context to a creative agent that runs `list_creatives` to find matching assets.

All API requests run through a secure V8 isolate sandbox on Vinkius. Your Kevel API keys are encrypted at rest and injected only during runtime, meaning your advertiser IDs and campaign configurations are never exposed to the LLM provider.

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