How to Use the Autobidder MCP in OpenAI Agents SDK

Q: How do I configure Autobidder with the OpenAI Agents SDK?

Install the SDK via pip and use MCPServerStreamableHttp to connect to the Vinkius MCP endpoint. You then pass this server instance into the Agent constructor within an async context manager to auto-discover the bidding tools.

Q: Can I trace Autobidder tool execution in the OpenAI dashboard?

Yes, every call to getbid or listprojects made by your agent gets logged in your OpenAI developer dashboard. This gives you the exact parameters passed and the payload returned for each bidding run.

Control your ad spend programmatically by connecting Autobidder to your OpenAI Agents SDK workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Autobidder MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track live ad bid outcomes with OpenAI Agents SDK

Your autonomous agents can now pull real-time ad performance data directly into their decision loops. By invoking `list_outcomes` and `get_outcome`, the agent evaluates which bidding strategies actually won placements without you writing custom API glue code. The OpenAI Agents SDK manages these MCP tool calls safely by validating the returned bid structures before letting the agent hand off tasks to your budget-monitoring agents. This setup keeps your ad spend constrained within your predefined safety guardrails.

Automate bid requests with guardrails

Instantly launch new bidding campaigns by letting your OpenAI agent execute `create_request` and `list_requests`. The agent checks your current profile with `get_profile` to match bids against your existing account limits. If the agent tries to execute an out-of-bounds bid request, the SDK's built-in validation catches the mistake before it reaches the Autobidder API. You get full visibility of these schema validations directly inside your OpenAI developer tracing dashboard using this MCP Server.

Monitor live projects and bid statuses

Keep your budget agents informed of active campaigns by exposing `list_projects` and `get_bid` to your agent loop. The agent queries these endpoints to verify whether a specific ad project requires a bid adjustment or a manual pause. Running this Autobidder MCP Server within the SDK's async context manager ensures your agent handles thousands of concurrent bid checks without blocking the main event loop.

Setup guide

Set up Autobidder 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 Autobidder tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the SDK via pip and use `MCPServerStreamableHttp` to connect to the Vinkius MCP endpoint. You then pass this server instance into the `Agent` constructor within an async context manager to auto-discover the bidding tools.

Yes, you can filter the tool list during initialization before passing them to the agent. This prevents your agent from calling `create_request` while still allowing it to query `list_bids` for reporting.

The SDK monitors the connection state and throws a runtime exception if the Vinkius endpoint drops. Your agent can proactively run `check_autobidder_status` to verify API connectivity before running high-value bidding logic on the MCP Server.

Yes, every call to `get_bid` or `list_projects` made by your agent gets logged in your OpenAI developer dashboard. This gives you the exact parameters passed and the payload returned for each bidding run.

Vinkius runs this MCP server inside an isolated V8 sandbox, meaning your API tokens and budget parameters never persist on disk. All communication between your OpenAI agents and the bidding API is encrypted in transit and executed within ephemeral runtimes.

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