How to Use the Kontak MCP in OpenAI Agents SDK

Q: Can my OpenAI agent read old text messages in Kontak?

Yes. The agent calls listkontakmessages to pull the recent history. It can filter sent and received texts to understand the conversation context before replying.

Connect the Kontak MCP Server to your OpenAI Agents SDK system. Send outbound SMS and audit message logs with full tracing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kontak MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Send SMS with OpenAI Agents SDK

The `send_outbound_sms` tool lets your agent fire off text messages directly from your Python application. You pass the target number and the text payload, and the Kontak MCP Server handles the delivery. If a message fails, your agent catches the error immediately. You can pair this with `get_message_details` to verify delivery status before triggering the next step in your workflow.

Audit communications and webhooks

The `get_kontak_audit_logs` tool pulls the raw system events straight into your agent's context window. Your OpenAI client reads these logs to monitor API usage and spot unauthorized access attempts. When you need to check routing, `list_kontak_webhooks` exposes your current event endpoints. Your agent can validate these configurations against your security policies without you writing a separate audit script.

Manage contacts and templates

Reading contact records requires the `list_kontak_contacts` and `get_contact_details` MCP tools. Your agent pulls the phone numbers and custom fields it needs before formatting an outbound message. Formatting happens through `list_kontak_templates` and `list_kontak_tags`. The agent grabs the approved template string, injects the contact data, and sends the text, keeping your messaging consistent.

Setup guide

Set up Kontak 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 Kontak tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the openai-agents package via pip. Create an MCPServerStreamableHttp instance with your endpoint URL and pass it to the mcp_servers array in your Agent constructor. Tools auto-discover immediately.

Yes. The agent calls list_kontak_messages to pull the recent history. It can filter sent and received texts to understand the conversation context before replying.

Set cacheToolsList=True when initializing the MCP Server connection. This stops the agent from refetching the tool schemas on every single request, speeding up your execution time.

You configure that in your guardrails. Since the SDK traces every action, a failed send_outbound_sms call registers as an error in your OpenAI dashboard.

Your OpenAI agent processes raw phone numbers and text message bodies when calling Kontak tools. The Vinkius V8 Isolate Sandbox destroys the memory state the second the request finishes. Zero data persists on the middleware layer.

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