How to Use the Authkey MCP in OpenAI Agents SDK

Q: How does OpenAI Agents SDK handle Authkey rate limits?

The SDK relies on your agent's error-handling loops. When sendsms returns a rate limit error, the agent can read the status code and back off before retrying.

Trigger transactional SMS and verify OTPs directly from your production OpenAI Agents SDK pipelines with built-in safety guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Authkey MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Secure OTP verification with OpenAI Agents SDK

This MCP Server exposes `send_otp` and `verify_otp` so your autonomous agents can handle user verification without human intervention. By exposing these capabilities via this server, you let specialized agents issue and check one-time passwords autonomously. The SDK's built-in guardrails keep these actions safe, preventing your agents from spamming users or executing unauthorized verifications. Tracing every verification attempt happens directly in your OpenAI developer dashboard. If a verification fails, your agent doesn't have to guess why. It checks `check_authkey_status` to see if the gateway is reachable or if the user simply made a typo.

Multi-agent SMS campaigns with strict guardrails

You can trigger bulk messaging campaigns directly from your Python pipelines using the `send_bulk_sms` and `send_sms` tools. This MCP Server lets you divide the labor between a copywriter agent and a distribution agent using OpenAI's native handoffs. The copywriter drafts the message, hands off to the distribution agent, and that agent sends the messages only after validating the recipient list against your safety rules. You track the entire lifecycle of the campaign through the OpenAI tracing dashboard. Monitoring exactly when `list_sms_history` is called allows you to verify delivery. This architecture prevents runaway loops and ensures you never send unintended messages to your customer database.

Voice and email fallbacks using agent handoffs

Your agents can query `get_sms_status` and `get_email_status` to automatically route users to fallback channels when delivery reports look bad. Your OpenAI Agents SDK setup can automatically route users to voice or email when SMS delivery reports indicate carrier delay. The agent checks the SMS status first, and if a delay is detected, it hands the task to a fallback agent that triggers `send_voice` or `send_email`. This multi-agent coordination happens in milliseconds. You define the routing logic in Python, and the agents execute the tool calls based on real-time feedback from `get_voice_status`.

Setup guide

Set up Authkey 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 Authkey tools at runtime.
3

Create your Agent

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

Run the agent

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

You pass your Vinkius endpoint token when initializing the MCPServerStreamableHttp client. The SDK handles the underlying MCP transport, making all 13 Authkey tools instantly discoverable by your agents.

Yes. You can limit MCP tool exposure during agent initialization or use the SDK's guardrail system to block tools like `send_bulk_sms` while keeping `send_otp` active.

The SDK relies on your agent's error-handling loops. When `send_sms` returns a rate limit error, the agent can read the status code and back off before retrying.

Set cacheToolsList to True in your server configuration. This prevents the SDK from querying Vinkius for the tool definitions on every single agent loop, speeding up response times.

Phone numbers and OTP codes transit through an isolated V8 sandbox hosted by Vinkius. No data is stored on our servers, and communication with the gateway is encrypted end-to-end.

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