How to Use the Dexatel MCP in OpenAI Agents SDK

Q: How do I install the Dexatel server in OpenAI Agents SDK?

Run pip install openai-agents. You initialize MCPServerStreamableHttp with your endpoint URL, then pass it directly into the mcpservers array in your Agent constructor.

Q: Does OpenAI Agents SDK cache the Dexatel tool list?

It does. Set cacheToolsList=True in your configuration. This prevents the agent from re-fetching the available tool schemas on every single execution loop.

Q: How do I handle failed deliveries?

Give your agent access to listfailedsmsdeliveries. Write an instruction that tells it to fetch failures hourly and output a summary report to your engineering channel.

Q: Is my contact address book secure?

Your agent accesses names and phone numbers via listmessagingcontacts through a V8 Isolate Sandbox. The MCP connection is ephemeral and zero-trust, meaning the data only exists in memory during the execution phase and vanishes immediately after.

Connect the Dexatel MCP Server to OpenAI Agents SDK and give your production agents direct SMS capabilities with built-in safety tracing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dexatel MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Send and track SMS from OpenAI Agents SDK

The `send_sms_message` tool fires off text messages directly to specific numbers. You hand it the payload, and the agent executes the delivery. Before sending out thousands of alerts, your agent hits `get_account_balance_metadata` to confirm you actually have the funds to cover the blast. Production environments demand oversight. Map `list_failed_sms_deliveries` to a specialized monitoring agent that triggers handoffs when failure rates spike. The SDK's built-in tracing tracks exactly which agent invoked this MCP Server tool, keeping your communication logs completely transparent.

Manage sender IDs and templates

The `list_authorized_sender_ids` tool pulls down every approved virtual number your account legally sends from. Carriers block unrecognized sender IDs constantly. Your agent reads this list first, ensuring it only dispatches messages through verified channels. You avoid agents hallucinating compliance text. By calling `list_sms_templates`, your agent retrieves pre-approved message structures. It fills in the blanks instead of writing from scratch, keeping your automated outreach strictly within carrier regulations.

Audit contact history and message details

The `get_contact_profile` tool dumps the complete interaction history for any specific contact in your address book. When a user replies with a support request, your agent pulls their profile to read past context before doing anything else. If a message gets flagged, you need specifics fast. The `get_sms_message_details` tool returns the exact delivery status and timestamps for a single text. Combine this with `search_sms_by_content` to let your agent hunt down specific keywords across your entire messaging history.

Setup guide

Set up Dexatel 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 Dexatel tools at runtime.
3

Create your Agent

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

Run the agent

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

Run `pip install openai-agents`. You initialize `MCPServerStreamableHttp` with your endpoint URL, then pass it directly into the `mcp_servers` array in your Agent constructor.

Yes. Write custom guardrails that force the agent to verify against `list_authorized_sender_ids` before it attempts any outbound communication.

It does. Set `cacheToolsList=True` in your configuration. This prevents the agent from re-fetching the available tool schemas on every single execution loop.

Give your agent access to `list_failed_sms_deliveries`. Write an instruction that tells it to fetch failures hourly and output a summary report to your engineering channel.

Your agent accesses names and phone numbers via `list_messaging_contacts` through a V8 Isolate Sandbox. The MCP connection is ephemeral and zero-trust, meaning the data only exists in memory during the execution phase and vanishes immediately after.

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