How to Use the SmartChatAI MCP in OpenAI Agents SDK

Q: How does SmartChatAI and OpenAI Agents SDK handle bot authentication?

You get account details by calling getauthenticateduserprofile. This ensures your agent only operates within the permissions assigned to the authenticated user. It's a core security step.

Q: Can SmartChatAI and OpenAI Agents SDK verify API status?

Absolutely. Use checkapihealth. This confirms that the entire MCP Server is operational before your production agents try to send messages, preventing deployment failures.

Q: What happens if I need to list all my configured webhooks with SmartChatAI and OpenAI Agents SDK?

You just run listconfiguredwebhooks. This shows you every active webhook endpoint. It's crucial for ensuring your production agents can communicate with external systems.

Building Production Agents with OpenAI Agents SDK and SmartChatAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect SmartChatAI MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Manage AI Bots via MCP Server

You can build, list, and get detailed configs for your bots using `list_ai_chatbots` and `get_chatbot_details`. This lets you manage the entire bot ecosystem from one place. Need to spin up a new agent? Use `create_new_ai_bot` when you need an AI assistant with a specific starting prompt. It handles the initial setup so your agents are ready to go.

Train Bots on External Data

Don't copy-paste data into prompts; train bots directly using `add_pdf_to_knowledge_base`. This tool processes PDFs, giving your agent deep context from complex documents. If you have raw text or a website you want the bot to reference, use `add_text_to_knowledge_base` or `add_website_to_knowledge_base`. The knowledge base updates immediately for your agents to use.

Send Messages and Track History

Want the agent to talk? Send a message using `message_ai_chatbot`, and you get an immediate reply. This is how your conversational workflows run. You can track what happened by calling `get_bot_chat_history`. It retrieves full conversation transcripts, letting you audit exactly who said what.

Setup guide

Set up SmartChatAI 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 SmartChatAI tools at runtime.
3

Create your Agent

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

Run the agent

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

You get account details by calling `get_authenticated_user_profile`. This ensures your agent only operates within the permissions assigned to the authenticated user. It's a core security step.

The platform supports three main sources: PDFs, raw text strings, and URLs. You use `add_pdf_to_knowledge_base` for structured documents, while the other tools handle basic content ingestion.

Absolutely. Use `check_api_health`. This confirms that the entire MCP Server is operational before your production agents try to send messages, preventing deployment failures.

You just run `list_configured_webhooks`. This shows you every active webhook endpoint. It's crucial for ensuring your production agents can communicate with external systems.

This server touches user account profiles, chat conversation transcripts, and webhook configuration details. Always ensure the underlying data is scrubbed before ingestion if PII is involved.

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