How to Use the ProTexting MCP in OpenAI Agents SDK

Q: How do I connect ProTexting to the OpenAI Agents SDK?

Install the SDK via pip. Initialize MCPServerStreamableHttp with your endpoint URL and pass it to your Agent constructor in the mcpservers list. The system auto-discovers all 12 messaging and contact tools.

Q: Does the ProTexting MCP Server support MMS attachments through OpenAI Agents SDK?

It does. Your agent calls sendmms with a valid media URL. The OpenAI tracing dashboard logs the exact payload, so you can verify the image link before the message hits carrier networks.

Q: How do I manage contact lists with this integration?

Your agent uses listcontacts to pull existing numbers and createcontact to add new ones. You can script the agent to automatically segment users by calling creategroup based on conversation history.

Build production-grade SMS marketing workflows using the OpenAI Agents SDK and built-in safety guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect ProTexting MCP to OpenAI Agents SDK

Create your Vinkius account to connect ProTexting to OpenAI Agents SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup ProTexting with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate SMS Campaigns with OpenAI Agents SDK

Connect your OpenAI agent directly to ProTexting to fire off targeted text blasts. By calling `send_bulk` and `send_mms`, your Python scripts distribute promotional codes or emergency alerts to thousands of numbers without manual intervention. You get full tracing in the OpenAI dashboard for every message sent. If your marketing agent spots a new lead, it instantly triggers `create_contact` and assigns them to a specific list using `create_group`, all while staying within your defined execution guardrails.

Monitor ProTexting Account Health and Status

Blindly sending texts is a great way to hit API limits and burn your budget. Your agent uses `get_account` to read remaining credit balances before executing large campaigns. If a pipeline stalls, the agent runs `check_protexting_status` to verify connectivity. You can set strict handoff rules so if the balance drops too low, the execution pauses and alerts a human instead of failing silently mid-run.

Track Delivery Metrics via this MCP Server

This MCP Server lets your agent confirm delivery receipts instead of just firing and forgetting. Calling `get_message_status` pulls exact carrier responses back into your Python environment. When you combine this with `list_keywords`, you can build an autonomous workflow that matches incoming keyword responses to outbound delivery success rates. The agent analyzes the conversion data and adjusts the next batch accordingly.

Setup guide

Set up ProTexting 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 ProTexting tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the SDK via pip. Initialize `MCPServerStreamableHttp` with your endpoint URL and pass it to your Agent constructor in the `mcp_servers` list. The system auto-discovers all 12 messaging and contact tools.

Yes. You can configure safety guardrails in your agent to throttle `send_bulk` calls. If ProTexting returns a 429 error, the agent catches it and backs off based on your defined retry logic.

It does. Your agent calls `send_mms` with a valid media URL. The OpenAI tracing dashboard logs the exact payload, so you can verify the image link before the message hits carrier networks.

Your agent uses `list_contacts` to pull existing numbers and `create_contact` to add new ones. You can script the agent to automatically segment users by calling `create_group` based on conversation history.

Your agent processes raw phone numbers, message bodies, and carrier delivery receipts. The MCP protocol routes this data directly between your local Python runtime and the ProTexting API. OpenAI only sees the payloads if you explicitly log them to their telemetry dashboard.

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