How to Use the Measured MCP in OpenAI Agents SDK

Q: What happens if an integration goes offline?

Your agent can call listintegrations to check the status of your data feeds. If a feed is broken, the agent detects the missing data and alerts your team instead of making decisions based on stale campaign metrics.

Feed real incrementality metrics directly to your OpenAI Agents SDK pipelines to adjust ad spend without manual exports.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Measured MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time ROAS audits via OpenAI Agents SDK

The `get_performance_summary` tool gives your agent instant access to your cross-channel marketing spend and performance metrics. Instead of writing custom scripts to pull data from separate ad platforms, you pass this MCP Server directly to your OpenAI agent to read your unified marketing data. Your agent runs these audits inside the OpenAI Agents SDK runtime, using the built-in guardrails to verify the performance thresholds before recommending budget shifts. This setup lets you build autonomous media-buying agents that can check `list_reports` and flag underperforming campaigns without human intervention.

True incrementality testing without tracking pixels

The `get_incrementality_scores` tool exposes the actual lift of your marketing channels, stripping away the inflated attribution numbers from self-reporting ad networks. Your agent queries this endpoint to see which channels drive net-new customers rather than just claiming credit for existing demand. By integrating this MCP Server with your OpenAI Agents SDK deployment, you can configure a specialized agent that compares these scores against current campaign data. The agent uses `get_campaign_performance` to identify where you are overpaying for view-through conversions and suggests immediate reallocations.

Automated channel and integration mapping

The `list_channels` tool pulls your active marketing channels directly into the agent's context window. Your agent can instantly map these channels against your active data pipelines using `list_integrations` to verify that no tracking gaps exist. This means your OpenAI Agents SDK setup can automatically detect when a new platform is added to your Measured dashboard. The agent then queries `get_insights` to extract performance trends for that specific channel, keeping your marketing reports current without manual intervention.

Setup guide

Set up Measured 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 Measured tools at runtime.
3

Create your Agent

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

Run the agent

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

You do not need to manage API keys inside your agent code. Vinkius handles the authentication, exposing a single secure endpoint token that you pass to the MCPServerStreamableHttp constructor in your OpenAI Agents SDK script.

No. This MCP Server is strictly read-only, exposing tools like `get_performance_by_channel` and `get_campaign_performance`. Your agents can analyze data and recommend shifts, but they cannot execute budget changes directly.

Set cacheToolsList=True during your server initialization to minimize schema queries. When your agent calls `get_insights`, Vinkius routes the request through its V8 sandbox to ensure stable execution without hitting API rate thresholds.

Your agent can call `list_integrations` to check the status of your data feeds. If a feed is broken, the agent detects the missing data and alerts your team instead of making decisions based on stale campaign metrics.

Yes. Vinkius runs the server in an ephemeral, zero-trust V8 Isolate sandbox. Your raw marketing performance and attribution data are never stored or used to train models; they only pass through to your OpenAI Agents SDK runtime.

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