Can I check a customer's points balance via AI?

Yes! Use the `get_customer_balance` tool and provide the Customer ID. Your agent will retrieve the current points and the loyalty tier for that specific user.

How do I award points for a recent purchase using the agent?

Use the `process_loyalty_transaction` action. Provide the Customer ID and the transaction amount. The agent will instantly calculate and award the correct points based on your Swarm settings.

Is it possible to list all the rewards a customer can claim?

Absolutely. Use the `list_available_rewards` query and provide the Customer ID. The agent will return the catalog of rewards that the user is currently eligible to redeem.

INSTANT PLUG AND PLAY

Swarm MCP Server for OpenAI Agents SDKGive OpenAI Agents SDK instant access to 5 tools to Get Customer Balance, List Available Rewards, List Customer Vouchers, and more

Name: Swarm
Availability: InStock
Author: Vinkius

Built by Vinkius GDPR 5 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Swarm through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Use with Your AI Agent

Ask AI about this App Connector for OpenAI Agents SDK

Open in ChatGPT Open in Claude Open in Perplexity

The Swarm app connector for OpenAI Agents SDK is a standout in the Marketing Automation category — giving your AI agent 5 tools to work with, ready to go from day one.

Vinkius delivers Streamable HTTP and SSE to any MCP client

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Swarm Assistant",
            instructions=(
                "You help users interact with Swarm. "
                "You have access to 5 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Swarm"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Swarm MCP Server

Connect your Swarm loyalty account to any AI agent and simplify how you manage customer rewards, award points for transactions, and handle redemptions through natural conversation.

The OpenAI Agents SDK auto-discovers all 5 tools from Swarm through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Swarm, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Point Management — Retrieve real-time point balances and loyalty tiers for specific customer IDs.
Transaction Processing — Programmatically award points to customers by registering sale amounts and product data via AI.
Reward Redemption — Convert customer points into discount vouchers or specific rewards and list all active vouchers.
Catalog Discovery — Browse available rewards and check eligibility for specific customers instantly.
Voucher Oversight — List and query all unused discount codes currently assigned to a customer's profile.
Loyalty Lifecycle — Manage the entire customer reward journey directly from Claude, Cursor, or any MCP client.

The Swarm MCP Server exposes 5 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

All 5 Swarm tools available for OpenAI Agents SDK

When OpenAI Agents SDK connects to Swarm through Vinkius, your AI agent gets direct access to every tool listed below — spanning loyalty-programs, rewards-management, customer-retention, and more. Every call is secured with network, filesystem, subprocess, and code evaluation entitlements inside a sandboxed runtime. Beyond a simple connection, you get a full AI Gateway with real-time visibility into agent activity, enterprise governance, and optimized token usage.

get_customer_balance

Check customer loyalty points

list_available_rewards

List redeemable rewards

list_customer_vouchers

List active customer vouchers

process_loyalty_transaction

Process a sale and award points

redeem_customer_reward

Redeem points for a reward

Connect Swarm to OpenAI Agents SDK via MCP

Follow these steps to wire Swarm into OpenAI Agents SDK. The entire setup takes under two minutes — your credentials stay safe behind the Vinkius.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 5 tools from Swarm

Why Use OpenAI Agents SDK with the Swarm MCP Server

OpenAI Agents SDK provides unique advantages when paired with Swarm through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Swarm + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Swarm MCP Server delivers measurable value.

Automated workflows: build agents that query Swarm, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Swarm, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Swarm tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Swarm to resolve tickets, look up records, and update statuses without human intervention

Example Prompts for Swarm in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Swarm immediately.

"What is the point balance for customer 'cust_10293'?"

"Award points for a $150 purchase to customer 'cust_88231'."

"Show me all available rewards I can claim with 500 points."

Troubleshooting Swarm MCP Server with OpenAI Agents SDK

Common issues when connecting Swarm to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Swarm + OpenAI Agents SDK FAQ

Common questions about integrating Swarm MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.

Can I use multiple MCP servers in one agent?

Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.

Does the SDK support streaming responses?

Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.