How to Use the Blueshift MCP in OpenAI Agents SDK

Push Blueshift customer data into OpenAI Agents SDK pipelines with built-in action guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Blueshift MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated customer profile management

Your agent can fire `create_update_customer` to sync user states without manual database entry. It ensures your production environment stays current by pushing updates directly through the SDK. This MCP Server handles the handshake, letting your code focus on the logic. You get clean integration where every change is traced back through the OpenAI dashboard.

Monitor campaign performance via OpenAI Agents SDK

Use `get_campaign_performance` to pull live metrics into your agent's decision loop. It provides an immediate look at how your marketing efforts are moving the needle. You avoid context switching by having the agent summarize results. It reads the data and prepares the next step based on the actual output.

Track user behavior with Blueshift tools

The `track_event` tool logs specific user actions into your Blueshift account the moment they happen. Your agent acts as the bridge between raw interaction and marketing intelligence. This keeps your data pipeline moving in real-time. You rely on the agent to interpret the event history and decide what to trigger next.

Setup guide

Set up Blueshift 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 Blueshift tools at runtime.
3

Create your Agent

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

Run the agent

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

You instantiate an MCPServerStreamableHttp object using the provided URL. Pass that instance into your Agent constructor's mcp_servers list for immediate tool discovery.

Yes. Set cacheToolsList to True when you configure the server in your Python code. This reduces overhead and speeds up your agent's response time.

The SDK includes built-in guardrails that check your agent's actions before execution. This prevents unauthorized calls to tools like `create_update_customer`.

The server logs the error, and the SDK's tracing features capture the failure. You can debug the exact state of your agent from the dashboard.

Vinkius runs the server in an ephemeral V8 sandbox. Your customer PII is never stored locally and only exists in memory while the agent processes the request.

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