How to Use the FynCom MCP in OpenAI Agents SDK

Q: How do I use FynCom with the OpenAI Agents SDK to send a reward?

Your agent just needs to call the sendreward tool. The SDK handles the API call to the FynCom server, and you can watch the entire operation happen in your OpenAI dashboard's trace.

Q: Is it possible to track all payments sent through FynCom and the OpenAI Agents SDK?

Absolutely. The listrewardhistory tool gives you the transaction log directly from FynCom. On top of that, the OpenAI platform traces every tool call your agent makes, giving you two sources of truth.

Send real-time micro-rewards to users from your OpenAI Agents SDK, with built-in safety checks for every single transaction.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FynCom MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Rewards, Not Risk

Let's be real, you can't have an agent just firing off payments without supervision. With the OpenAI SDK's guardrails, you can build safety right into your agent's logic. Force a check on `get_wallet_balance` before any `send_reward` call is executed. This is how you prevent runaway scripts from draining your budget. It's a simple, effective backstop. The agent proposes the action, but your code gets the final say based on real-time data from the FynCom tools. That's how you move from a prototype to a production-ready system that the finance team can actually trust.

Manage Campaigns From Your Agent

Your agent shouldn't just be a trigger. It can manage the entire reward process. It starts by checking all active campaigns with `list_reward_campaigns` to see what's available. Then, it can use `get_campaign_details` to find the perfect campaign for a specific user action. Once it has a match, the agent registers the new user with `add_reward_lead`. This turns your agent into a smart operator that makes informed decisions, not just a dumb tool that executes a single command. It understands the context of your marketing efforts.

Full Transaction Tracing via MCP Server

When money is moving, you need a paper trail. Every call your agent makes to the FynCom MCP Server is logged and visible. You can see the full request and response for every `send_reward` or `get_wallet_balance` call directly in the OpenAI tracing dashboard. Combine that with the `list_reward_history` tool, and you have a complete, auditable record of every penny spent. It’s not a black box. You see exactly which agent did what, when, and why, which is critical for debugging and financial accountability.

Setup guide

Set up FynCom 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 FynCom tools at runtime.
3

Create your Agent

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

Run the agent

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

Your agent just needs to call the `send_reward` tool. The SDK handles the API call to the FynCom server, and you can watch the entire operation happen in your OpenAI dashboard's trace.

Yes. You use the SDK’s guardrails to enforce rules. For example, write a simple check that requires the agent to call `get_wallet_balance` and confirm funds are available before it’s allowed to execute a `send_reward` action.

It's automatic. When you pass the FynCom MCP server to the Agent constructor, it discovers all the available tools like `list_reward_campaigns` and `add_reward_lead` on its own. There's no manual mapping required.

Absolutely. The `list_reward_history` tool gives you the transaction log directly from FynCom. On top of that, the OpenAI platform traces every tool call your agent makes, giving you two sources of truth.

The server only touches the data required to process a reward. This includes campaign details, a lead identifier like an email, and your transaction history. Your agent's private thoughts and other conversations never leave the OpenAI environment.

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