How to Use the UpGuard MCP in OpenAI Agents SDK

Q: How does UpGuard help with identity breaches when using the OpenAI Agents SDK?

The MCP Server exposes listidentitybreaches, which lets your agent query known exposure points. This data feeds directly into your agent's decision-making process, ensuring that breach mitigation is a core part of the workflow.

Q: Can I check vendor risks with UpGuard and the OpenAI Agents SDK?

Yes. You first call listvendors to get a list of all monitored vendors. Then, you pass any specific vendor name into listvendorrisks, giving your agent targeted risk data for that partner.

Q: What kind of domain monitoring does UpGuard offer with the OpenAI Agents SDK?

The tool listmonitoreddomains provides a list of all domains UnderGuard is watching. This lets your agent verify if any external assets or forgotten subdomains are presenting an unmanaged risk.

Manage your attack surface risk using the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect UpGuard MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Detect Active Security Risks via MCP Server

Need to know what's going wrong right now? You can call `list_account_risks` to get a real-time list of all active risks tied to the account. This tells your agent exactly where the vulnerabilities are showing up, letting you prioritize patching before attackers do. Beyond general risk scores, you also have dedicated tools like `list_user_risks`. Checking these lets your agent drill down and pinpoint which specific users are presenting the highest level of security concern.

Map Out Your Entire Digital Footprint

Your agent needs to know everything you use. You'll find tools like `list_monitored_domains` and `list_monitored_ips`, which give a complete picture of your external assets. This isn't just checking boxes; it maps out every corner of the attack surface. Don't forget about third parties. Use `list_vendors` to get a roster of all monitored vendors, then use `get_vendor` on any specific name to assess their security details immediately.

Handle Identity and Application Vulnerabilities

The biggest risk often comes from who you trust. You can run `list_identity_breaches` to see a clear record of past breaches, and also use `list_user_risks`. This is critical for understanding the scope of identity exposure. If SaaS sprawl worries you, `list_saas_apps` shows every application under surveillance. Your agent can then cross-reference this list against known risks using `list_vendor_risks` to build a full picture.

Setup guide

Set up UpGuard 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 UpGuard tools at runtime.
3

Create your Agent

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

Run the agent

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

The MCP Server exposes `list_identity_breaches`, which lets your agent query known exposure points. This data feeds directly into your agent's decision-making process, ensuring that breach mitigation is a core part of the workflow.

Yes. You first call `list_vendors` to get a list of all monitored vendors. Then, you pass any specific vendor name into `list_vendor_risks`, giving your agent targeted risk data for that partner.

The tool `list_monitored_domains` provides a list of all domains UnderGuard is watching. This lets your agent verify if any external assets or forgotten subdomains are presenting an unmanaged risk.

The MCP Server provides direct, actionable security metrics like `list_account_risks`. This raw data allows your agent to validate its actions against known, real-world vulnerabilities.

This server touches identity breach records and user risk profiles. It specifically handles lists of identities found in `list_identity_breaches` and individual user threat scores from `list_user_risks`.

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