How to Use the Aspire MCP in OpenAI Agents SDK

Q: How do I connect the Aspire MCP Server to my OpenAI Agents SDK?

Install the SDK via pip, then initialize MCPServerStreamableHttp using your Vinkius endpoint. Pass this server instance into your agent's constructor inside an async context manager, and the SDK will auto-discover tools like listprojects instantly.

Q: Does this setup support caching for faster tool discovery?

Yes. Set cacheToolsList=True in your server parameters when initializing with the OpenAI Agents SDK. This caches the Aspire tool definitions, bypassing schema lookups on subsequent runs.

Run production-ready influencer marketing agents with the OpenAI Agents SDK and Aspire.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Aspire MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Guarded Campaign Audits via OpenAI Agents

Deploying autonomous agents to manage creators means you need hard boundaries. By connecting this MCP Server to your OpenAI Agents SDK setup, your agents can pull campaign details using `list_projects` and verify account health with `get_account_check` while respecting your predefined system guardrails. You won't have to worry about an agent going rogue and editing records without your explicit sign-off. The OpenAI dashboard logs every single tool call, giving you a complete trace of how your agent evaluated a specific Aspire marketing campaign. When the agent checks campaign performance, you see the exact payload returned, ensuring full transparency before any automated decisions are made.

Multi-Agent Creator Evaluation

You can split your creator management workload between specialized OpenAI agents. Have one agent run `get_member` to analyze Aspire creator profiles, then hand off the data to an analytics agent that calls `get_post` to run engagement numbers. This keeps your OpenAI agents focused on single tasks instead of getting confused by massive, mixed contexts. Implementing this is straightforward because you register the Aspire server under your agent's tool list, and the SDK handles the handoff logic.

Real-Time Performance Tracking

Keep your production systems updated by letting your OpenAI agents pull active social metrics on demand. The agent calls `list_posts` to monitor live content performance, matching actual numbers against your Aspire campaign goals using this MCP setup. To keep performance snappy in production, you can set `cacheToolsList=True` during initialization. This prevents the OpenAI Agents SDK from repeatedly querying the Aspire server schema, keeping your runtime fast and your API usage efficient.

Setup guide

Set up Aspire 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 Aspire tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the SDK via pip, then initialize `MCPServerStreamableHttp` using your Vinkius endpoint. Pass this server instance into your agent's constructor inside an async context manager, and the SDK will auto-discover tools like `list_projects` instantly.

Yes. You can control tool access directly through the OpenAI Agents SDK routing layer or by defining strict system instructions. This ensures your agent only reads campaign data with `list_campaigns` and does not execute unauthorized checks.

The SDK handles API calls asynchronously, allowing you to build backoff logic around tools like `list_posts`. This prevents your agent from hitting rate limits when pulling heavy performance data for large-scale campaigns.

Yes. Set `cacheToolsList=True` in your server parameters when initializing with the OpenAI Agents SDK. This caches the Aspire tool definitions, bypassing schema lookups on subsequent runs.

Your creator profiles and campaign performance metrics never sit on external servers. The connection runs through Vinkius's secure sandboxed MCP environment, meaning your proprietary influencer data is only visible to your active OpenAI agent sessions and never used for training.

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