How to Use the Bandwidth Alternative MCP in OpenAI Agents SDK

Q: Can the OpenAI Agents SDK fetch Bandwidth Alternative account details?

Yes, the agent calls the getaccountinfo tool directly. This returns your current balance and configuration settings. You route this data to a billing dashboard using a specialized reporting agent.

Q: Does the framework support handoffs?

Handoffs function exactly as expected. One agent runs listphonenumbers to find an available caller ID. It then transfers control to a separate agent that executes the makecall command.

Q: How do I list registered applications?

Your agent invokes the listapplications tool to pull your configured voice and messaging apps. The results appear in your standard OpenAI traces. You see the raw JSON response right in your dashboard.

Build production voice and SMS agents using the OpenAI Agents SDK to connect your models directly to Bandwidth Alternative.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bandwidth Alternative MCP to OpenAI Agents SDK

Create your Vinkius account to connect Bandwidth Alternative 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 Bandwidth Alternative with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger outbound calls with this MCP Server

The `make_call` tool gives your OpenAI agent direct access to initiate voice sessions. You set up the guardrails in your Python code, defining exactly when and how the model can dial out. Handoffs work perfectly here. A triage agent evaluates a customer issue, then passes control to a specialized outbound agent that triggers the actual call. Tracing stays completely visible in the OpenAI dashboard. Every time the agent queries `get_call_state` to check if a user picked up, you see the exact payload and latency. The model knows the line status before proceeding with its next step.

Audit active voice conferences

Using the `list_conferences` tool lets your agent monitor live multi-party calls. You define the logic in your Python script to pull active participant data on a schedule. The model evaluates the state and triggers alerts if a conference drops unexpectedly. You build a complete picture of your voice traffic by combining this with `list_calls`. Your production system tracks recent activity without manual intervention. If an anomaly appears, the agent flags it immediately in your logs.

Dispatch SMS messages securely

Calling the `send_sms` tool pushes text messages straight from your automated workflows. You restrict the destination numbers using the OpenAI Agents SDK safety constraints. The agent only texts authorized contacts, preventing runaway billing charges. You track delivery through the `list_messages` tool. Your system confirms the text arrived and logs the timestamp. You skip the custom API integration completely because this MCP Server auto-discovers its tools on startup.

Setup guide

Set up Bandwidth Alternative 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 Bandwidth Alternative tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package via pip and configure an MCPServerStreamableHttp object. Pass it to your Agent constructor in the mcp_servers array. Set cacheToolsList=True to speed up the initial auto-discovery phase.

Yes, the agent calls the get_account_info tool directly. This returns your current balance and configuration settings. You route this data to a billing dashboard using a specialized reporting agent.

Handoffs function exactly as expected. One agent runs list_phone_numbers to find an available caller ID. It then transfers control to a separate agent that executes the make_call command.

Your agent invokes the list_applications tool to pull your configured voice and messaging apps. The results appear in your standard OpenAI traces. You see the raw JSON response right in your dashboard.

Vinkius isolates every request inside a V8 sandbox. Your call logs and SMS histories pass through an ephemeral environment that destroys itself after execution. We never store your communication records.

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