How to Use the Liaison MCP in OpenAI Agents SDK

Q: What happens if the Liaison connection drops during an OpenAI Agents SDK session?

You can verify the connection status at any time using checkliaisonstatus. If the service is down, your agent will catch the error immediately and stop the process.

Q: Is it possible to filter custom fields using Liaison and my OpenAI Agents SDK?

Yes. Run listcustomfields to see exactly what metadata is available for your applicants. You can then map this info directly into your agent's context.

Connect your OpenAI Agents SDK to Liaison and automate applicant tracking without the manual data entry grind.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Liaison MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time applicant data retrieval

Your agent can grab specific applicant records directly from your Liaison instance. It uses `get_application` to pull the latest status updates and applicant details into your pipeline. Stop waiting on manual exports. By automating these calls, you get the latest data into your agent's hands as soon as it hits the server.

Program and designation mapping

Automate how your agents categorize incoming student data using `list_programs` and `list_designations`. This ensures your internal records match the exact academic structure defined in your admission system. Your agent handles the mapping logic. It keeps your CRM in sync with current academic offerings without needing human intervention.

Batch processing for high-volume admissions

Handle large applicant queues by triggering `list_batches` and `get_batch` through your agent. It pulls groups of records in one go, which keeps your processing speed high during peak enrollment cycles. This MCP Server lets your agent manage the heavy lifting. You define the batch trigger, and the agent processes the queue according to your safety guardrails.

Setup guide

Set up Liaison 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 Liaison tools at runtime.
3

Create your Agent

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

Run the agent

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

It provides direct, authenticated access to your admissions data. Your agent queries the API instantly instead of relying on slow, manual spreadsheet uploads.

No. This toolset is strictly read-only. It handles data retrieval tasks like `list_applications` to ensure your admissions records remain secure.

You can verify the connection status at any time using `check_liaison_status`. If the service is down, your agent will catch the error immediately and stop the process.

Yes. Run `list_custom_fields` to see exactly what metadata is available for your applicants. You can then map this info directly into your agent's context.

We use scoped tokens to limit access to your admissions data. The server only handles specific read requests for applicant records and program metadata, keeping your sensitive information isolated.

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