How to Use the Friendbuy MCP in OpenAI Agents SDK

Q: How do I configure the Friendbuy MCP Server with the OpenAI Agents SDK?

Use pip install openai-agents. Create the MCPServerStreamableHttp object with your endpoint URL. Pass it into the mcpservers array in your Agent constructor. Set cacheToolsList=True to speed up tool discovery.

Q: Can the OpenAI Agents SDK track new user signups in Friendbuy?

Yes. The agent calls trackconversionsignup when a user creates an account. You just need to pass the required customer identifiers in the tool payload.

Q: Does this integration support multi-agent handoffs?

It does. You can assign createreferralcode to an onboarding agent. Once the code exists, that agent passes control to a messaging agent to email the link to the user.

Q: How do I view the rewards data using Friendbuy and the OpenAI Agents SDK?

Your agent executes listreferralrewards to pull the array of granted bonuses. The SDK traces this API call automatically, so you can review the exact JSON response in your OpenAI dashboard.

Connect the Friendbuy MCP Server to the OpenAI Agents SDK to automate referral tracking and reward issuance with built-in guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Friendbuy MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate conversions with this MCP Server

`track_conversion_signup` and `track_conversion_purchase` let your agent log new users and their spending directly into your referral system. You trigger these actions straight from your Python application logic. The SDK validates the payload before execution, stopping malformed conversion data from corrupting your metrics. Handoffs make this powerful. One specialized agent handles user onboarding, then passes the context to a secondary agent that fires the conversion tool. You get full visibility into the execution chain through the OpenAI dashboard.

Manage reward pipelines programmatically

`list_referral_rewards` pulls the exact payout status for your users. Your agent reads this data to answer customer support queries about missing discounts or pending credits. It checks `list_tracked_purchases` to verify the underlying transactions that generated those rewards. You don't have to guess if the connection dropped. `check_api_connection` pings the endpoint to confirm authorization before running batch reward audits. If it fails, the agent halts the workflow and alerts your engineering team.

Generate and audit referral codes

`create_referral_code` generates unique share links on demand. You map this tool to your user registration flow, letting the agent provision codes instantly. It immediately follows up with `get_referral_code_status` to confirm the code is active and ready for distribution. Auditing infrastructure happens through `list_webhooks`. Your agent queries the active event listeners to ensure your backend is receiving the real-time callbacks. This integration keeps your tracking loop closed and accurate.

Setup guide

Set up Friendbuy 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 Friendbuy tools at runtime.
3

Create your Agent

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

Run the agent

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

Use `pip install openai-agents`. Create the `MCPServerStreamableHttp` object with your endpoint URL. Pass it into the `mcp_servers` array in your Agent constructor. Set `cacheToolsList=True` to speed up tool discovery.

Yes. The agent calls `track_conversion_signup` when a user creates an account. You just need to pass the required customer identifiers in the tool payload.

It does. You can assign `create_referral_code` to an onboarding agent. Once the code exists, that agent passes control to a messaging agent to email the link to the user.

Your agent executes `list_referral_rewards` to pull the array of granted bonuses. The SDK traces this API call automatically, so you can review the exact JSON response in your OpenAI dashboard.

This server handles sensitive purchase amounts and customer identifiers. The OpenAI Agents SDK executes tools within your secure Python environment. No transaction data leaks outside your defined guardrails during execution.

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