Bring Attack Surface
to OpenAI Agents SDK
Learn how to connect UpGuard to OpenAI Agents SDK and start using 9 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for SubscribersCompatible with every major AI agent and IDE
Gemini
What is the UpGuard MCP Server?
Connect your UpGuard account to any AI agent and simplify how you monitor your attack surface, assess third-party vendor risks, and protect your organization's digital assets through natural conversation.
What you can do
- Vendor Risk Assessment — List and query all monitored vendors to retrieve their security scores and metadata.
- Risk Monitoring — List active security risks detected across your own infrastructure (BreachSight) and your vendor network (VendorRisk).
- Data Breach Tracking — Monitor identity breaches affecting your workforce and retrieve detailed breach reports.
- Asset Visibility — List monitored domains, IP ranges, and SaaS applications to understand your digital footprint.
- Employee Security — Audit user-related risk data and identity theft exposures directly via AI commands.
How it works
- Subscribe to this server
- Enter your UpGuard API Key (found in your account settings)
- Start managing your cybersecurity posture from Claude, Cursor, or any MCP client
Who is this for?
- CISO & Security Analysts — quickly check security scores and identify critical infrastructure risks via simple AI queries.
- Procurement & Compliance — verify vendor risk profiles and monitor third-party security posture directly from the workspace.
- IT Operations — track monitored domains and IPs to maintain a secure and up-to-date asset inventory.
Built-in capabilities (9)
Get details for a specific vendor
List all active risks for the account
List identity breaches
List monitored domains
List monitored IP addresses
List monitored SaaS applications
List users and their risk data
List active risks for a vendor
List all monitored vendors
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 9 tools from UpGuard through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries UpGuard, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
- —
Native MCP integration via
MCPServerSse, pass the URL and the SDK auto-discovers all tools with full type safety - —
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
- —
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
- —
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
UpGuard in OpenAI Agents SDK
UpGuard and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect UpGuard to OpenAI Agents SDK through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for UpGuard in OpenAI Agents SDK
The UpGuard MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 9 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in OpenAI Agents SDK only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
UpGuard for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the UpGuard MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How do I check the security score of a specific vendor?
Use the get_vendor tool and provide the Vendor ID. Your agent will retrieve the complete security profile, including the overall score and metadata for that vendor.
Can I see all active risks across my entire account?
Yes! Use the list_account_risks query. This retrieves all active security risks detected across your own digital infrastructure (BreachSight).
Is it possible to monitor data breaches affecting our employees?
Absolutely. Use the list_identity_breaches query to retrieve data on identity breaches affecting your workforce, helping you take proactive security measures.
How does the OpenAI Agents SDK connect to MCP?
Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.
Can I use multiple MCP servers in one agent?
Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.
Does the SDK support streaming responses?
Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.
MCPServerStreamableHttp not found
Ensure you have the latest version: pip install --upgrade openai-agents
Agent not calling tools
Make sure your prompt explicitly references the task the tools can help with.
Explore More MCP Servers
View all →
BR Business Days Calculator
2 toolsStop LLMs from calculating SLAs incorrectly. An local, deterministic engine that adds business days while perfectly avoiding weekends and Brazilian national holidays.
Worldpay
9 toolsProcess payments, manage refunds, and audit settlements on Worldpay — the global leader in payment processing technology.
Better Stack
10 toolsMonitor uptime and incidents via Better Stack — list monitors, heartbeats, and on-call schedules directly from any AI agent.
Open WebUI
12 toolsManage your Open WebUI instance — list models, handle chat completions, and manage RAG collections directly from any AI agent.