How to Use the Expansify AI MCP in OpenAI Agents SDK

Q: How do I connect Expansify AI to the OpenAI Agents SDK?

Installs are straightforward. Run pip install openai-agents and initialize MCPServerStreamableHttp pointing to your Vinkius MCP Server endpoint. Pass this server instance inside the mcpservers list when instantiating your Agent.

Q: Can I cache tools when using Expansify AI with the OpenAI Agents SDK?

Yes. Set cacheToolsList=True in your configuration to avoid fetching the tool definitions on every turn. This keeps your agent latency low when calling generateaicontent repeatedly.

Q: Does Expansify AI support multi-agent handoffs in OpenAI Agents SDK?

It does. One agent can analyze search metrics using analyzekeywordseo, then hand off the structured data to a writing agent that triggers generateaicontent.

Q: How do I list my active marketing campaigns?

Your agent calls the listcampaigns tool. This returns all active campaign records stored on the server, which your agent can parse to plan next actions.

Run production marketing agents that build campaigns and track SEO using the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Expansify AI MCP to OpenAI Agents SDK

Create your Vinkius account to connect Expansify AI 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 Expansify AI with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track SEO keywords with OpenAI Agents SDK

The `analyze_keyword_seo` tool pulls search performance metrics directly into your agent's decision loop. Your agent uses this raw data to spot ranking drops and immediately adjust your content queue without you writing custom scraping scripts. By using `list_tracked_keywords`, your system monitors current rankings over time. The OpenAI Agents SDK runs these tools with built-in guardrails, making sure your agent only tracks approved terms before kicking off any new writing tasks.

Spin up campaigns from your pipeline

The `create_campaign` tool builds structured marketing campaigns directly from your Python runtime. You pass the target audience parameters, and the server registers the campaign shell instantly. To keep things organized, the agent calls `list_campaigns` to verify existing schedules. This prevents duplicate campaigns and lets your agent hand off tasks to specialized copywriter agents with clean state data.

Automate content drafts with safety guardrails

The `generate_ai_content` tool drafts marketing copy based on your active campaign parameters. It feeds raw drafts directly into your OpenAI agent, allowing immediate programmatic review. Your agent then calls `list_generated_content` to audit the output queue. Because you are using this MCP Server, the OpenAI tracing dashboard logs every single generation step, ensuring you see exactly what your agent creates.

Setup guide

Set up Expansify AI 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 Expansify AI tools at runtime.
3

Create your Agent

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

Run the agent

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

Installs are straightforward. Run `pip install openai-agents` and initialize `MCPServerStreamableHttp` pointing to your Vinkius MCP Server endpoint. Pass this server instance inside the `mcp_servers` list when instantiating your Agent.

Yes. Set `cacheToolsList=True` in your configuration to avoid fetching the tool definitions on every turn. This keeps your agent latency low when calling `generate_ai_content` repeatedly.

It does. One agent can analyze search metrics using `analyze_keyword_seo`, then hand off the structured data to a writing agent that triggers `generate_ai_content`.

Your agent calls the `list_campaigns` tool. This returns all active campaign records stored on the server, which your agent can parse to plan next actions.

All SEO keywords and campaign metadata stay isolated within your Vinkius V8 sandbox. The MCP Server processes this raw marketing data ephemerally, meaning no draft content or keyword logs are stored permanently on Vinkius servers.

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