How to Use the InfoVetted MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK handle multiple InfoVetted check types?

Yes, your agent can call listsupportedchecktypes to see what checks are available on the MCP Server. It can then initiate criminal background checks or employment history verifications using createnewvettingcheck based on the candidate's profile.

Q: What happens if the API goes down during a screening?

Your agent can run checkapiconnectivity to verify the connection status. If the API is unreachable, the agent can pause its workflow, log the issue to your OpenAI dashboard, and retry the check later.

Run safe background checks by giving your OpenAI Agents SDK direct access to automated candidate screening tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect InfoVetted MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger background checks safely inside OpenAI Agents SDK

The `create_new_vetting_check` tool lets your production agent start candidate screenings without manual steps. By passing this MCP Server to your agent constructor, it gets instant access to `create_new_vetting_check` and `create_screening_contact`. You can validate these actions using the SDK's built-in guardrails before any criminal record searches or education verifications actually run. Writing custom integration code for every background check is a thing of the past. The agent auto-discovers the tools and can hand off the verification task to a specialized compliance agent. This agent can query `list_supported_check_types` to choose the correct screening level for each candidate's location.

Automate candidate tracking and group sorting

Managing your candidate pipeline is a mess when done manually. This MCP Server lets your agent run `create_contact_group` to segment applicants by department, like engineering or sales. Once the group is ready, the agent registers the candidate using `create_screening_contact` and adds them to the correct category without human intervention. The OpenAI dashboard traces every single tool call, showing you exactly when the agent grouped a contact or queried `get_contact_details`. Recruiters get complete transparency to audit the decision-making process of your hiring pipeline at any time.

Monitor screening status in real time

The `get_vetting_request_status` tool lets your agent monitor screening progress in real time. Your agent can poll `get_vetting_request_status` or inspect the list of active checks via `list_vetting_requests`. If a check hangs or takes too long, the agent can use `cancel_active_vetting` to stop the process before incurring extra costs. You can also inspect `list_configured_webhooks` to see how the platform notifies your system. The MCP integration handles these status checks in the background, keeping your recruitment database updated without relying on human polling.

Setup guide

Set up InfoVetted 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 InfoVetted tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the SDK with pip and initialize the server using the Streamable HTTP params class. Pass the server endpoint directly into your Agent constructor. The agent will automatically discover tools like `check_api_connectivity` and start running checks.

Yes, your agent can call `list_supported_check_types` to see what checks are available on the MCP Server. It can then initiate criminal background checks or employment history verifications using `create_new_vetting_check` based on the candidate's profile.

The SDK has built-in guardrails that intercept tool calls. When the agent attempts to run `create_new_vetting_check`, you can require manual approval or run validation logic in your Python code before the API is hit.

Your agent can run `check_api_connectivity` to verify the connection status. If the API is unreachable, the agent can pause its workflow, log the issue to your OpenAI dashboard, and retry the check later.

All criminal record searches and education verification data are processed within a zero-trust V8 sandbox. This MCP Server handles authentication securely so your API credentials are never exposed to the LLM, and candidate records accessed via `get_contact_details` are transmitted over encrypted channels without persistent storage on our servers.

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