How to Use the Ada MCP in OpenAI Agents SDK

Give your OpenAI Agents SDK bots direct access to Ada support logs and knowledge bases for real-time customer context.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ada MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe Ada Article Creation with OpenAI Agents SDK

Run your help center updates through the SDK's built-in guardrails before pushing them live. When your agent wants to run `create_article`, the SDK validates the text structure and content safety to prevent corrupt or inappropriate help articles from hitting your public Ada knowledge base. This strict validation keeps your support bot reliable. If an agent tries to write a bad article, your OpenAI dashboard flags the trace immediately, giving you full visibility into what your agent tried to publish.

Trace End-User Profile Lookups on the Dashboard

Pull customer profiles using `get_end_user` while tracking every data access event inside the OpenAI tracing timeline. Your production agent can inspect custom metavariables to decide if it should hand off a complex support case to a human agent. This handoff happens without losing context. Because the SDK manages agent-to-agent transitions, the receiving agent gets the exact user profile fetched from Ada, ensuring your customer never has to repeat their issue.

Audit Support Chats via the OpenAI Agents SDK MCP Server

Monitor how your automation behaves by letting your agent pull chat history with `list_conversations`. The SDK inspects these past interactions to evaluate if your live bot is actually solving customer problems or just looping. You get a clean view of active and past support sessions directly in your Python runtime. Since the SDK auto-discovers this MCP Server, your agents can inspect these logs and update the help index using `list_articles` without manual tool registration.

Setup guide

Set up Ada 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 Ada tools at runtime.
3

Create your Agent

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

Run the agent

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

You configure your Ada credentials once on Vinkius. The OpenAI Agents SDK connects via the secure streamable HTTP endpoint, meaning your Python code never handles raw API keys or exposes support databases to the client.

Yes, that is a core benefit of this SDK. You can write custom verification logic in Python that intercepts the `create_article` tool execution, ensuring no agent publishes unapproved support content.

The SDK auto-discovers all four tools when you pass the MCP endpoint to the Agent constructor. Setting the tool list cache to true ensures your agents immediately know how to use `list_conversations` and `get_end_user` without latency.

Yes, the SDK is built for multi-agent handoffs. One agent can pull the customer history with `list_conversations`, determine the specialized department needed, and hand the context off to another agent to resolve the issue.

Your support histories and end-user profiles are protected by Vinkius's isolated sandbox environment. The MCP server processes `list_conversations` data in memory, never storing customer logs or support articles on persistent disks, keeping your customer support records compliant.

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