How to Use the Aidbase MCP in OpenAI Agents SDK

Q: Where do I check if my support endpoints are online?

Use checkaidbasestatus within your agent's routing logic to verify the API is up before processing user tickets. If the ping fails, your system routes requests to offline storage automatically.

Connect your OpenAI Agents SDK to your Aidbase MCP Server for secure, production-grade ticket resolution.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Aidbase MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed Aidbase documentation directly from OpenAI Agents SDK

`add_aidbase_website_knowledge` injects live web pages straight into your customer support models. Your Python-based OpenAI agent runs this tool when it detects outdated support docs during customer chats, triggering an instant crawl without requiring manual file uploads. This process runs inside OpenAI's sandboxed execution layer, keeping your raw web scraping actions isolated. You inspect the tool's payload on your OpenAI dashboard to ensure only public documentation gets added to your Aidbase system.

Securely reply to tickets using this custom MCP Server

`send_aidbase_reply` transmits your agent's drafted resolutions back to active customer threads. Before executing this action, your OpenAI Agents SDK configuration applies strict validation guardrails to prevent hallucinated answers from reaching real customers. If the OpenAI model generates a weird response, the SDK's built-in validation blocks the outbound Aidbase call. You get full visibility of these blocked customer messages in your main OpenAI dashboard, letting you patch prompts before they break your support metrics.

Audit chatbot knowledge bases programmatically

`list_aidbase_chatbot_knowledge` pulls the exact training sources assigned to your active support widgets. Your OpenAI agent calls this to cross-reference customer questions against your existing docs, determining if it needs to hand off the conversation to a human teammate. By running this check programmatically, your OpenAI multi-agent architecture avoids redundant Aidbase lookups. You save OpenAI token costs by filtering out irrelevant knowledge before feeding context to the core LLM.

Setup guide

Set up Aidbase 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 Aidbase tools at runtime.
3

Create your Agent

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

Run the agent

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

You install openai-agents and initialize the connection using the Vinkius single endpoint token. The SDK automatically detects tools like list_aidbase_chatbots and exposes them to your agent constructor without manual mapping.

Yes, you control this at the agent definition level by passing a filtered tool list to the constructor. This prevents a customer-facing bot from calling administrative tools like add_aidbase_faq_item while still allowing read-only access.

The SDK catches the connection error and bubbles it up through your standard Python exception handlers. Your agent can then run a fallback step, like routing the customer to a human queue instead of stalling.

Use check_aidbase_status within your agent's routing logic to verify the API is up before processing user tickets. If the ping fails, your system routes requests to offline storage automatically.

All support logs and ticket replies pass through a zero-trust V8 sandbox that destroys the runtime environment immediately after execution. Your raw support data never rests on Vinkius servers, maintaining strict compliance with your data retention policies.

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