How to Use the UpGuard MCP in Cursor

Q: How does UpGuard work with Cursor for code generation?

The MCP Server allows your AI client to call tools like listuserrisks directly into the context. The agent then writes working code that incorporates the live risk data, meaning you don't have to switch out of your editor.

Q: What data does UpGuard handle regarding identity breaches when used with Cursor?

The server touches records from listidentitybreaches. This means the AI can write code that handles lists of breached identities, letting you build immediate checks into your application logic.

Q: If I need to check vendor credentials, how does UpGuard work with Cursor?

You use getvendor and then chain the results through listvendorrisks. This sequence lets the AI client write code that accepts a vendor name parameter and returns a list of associated risks.

Q: Does UpGuard support listing user risks in Cursor?

Yes. The tool listuserrisks provides current user risk data, letting your AI client write code that validates permissions or flags accounts based on the returned risk level.

Inject real-time security context into your code flow using Cursor's agent mode.

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 Cursor

Create your Vinkius account to connect UpGuard to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Code Against Vendor Risk

The `get_vendor` tool lets the AI write code that pulls specific vendor details when you request it. You can then pass those results to `list_vendor_risks`, which allows the agent to generate working functions that incorporate current security risk statuses. Don't use mock data for security checks. The live API response from UpGuard lets your AI client write code using real, active risk metrics.

Build Identity Checkers

You can build functions that call `list_identity_breaches` to check if a user's credentials are exposed. The agent takes this list and lets you inject it directly into the code structure you're writing. Need to track accounts? Use `list_account_risks` in your project scope, letting the AI use that live data as input variables for your functions.

Map Out Assets in Code

Use the tools like `list_monitored_domains` and `list_saas_apps` to populate arrays or configuration objects. The AI takes these lists and writes code that validates them against your application's current assets. For a complete picture of infrastructure, you can run `list_vendors` first, then use the resulting names in other functions.

Setup guide

Set up UpGuard MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the UpGuard MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent UpGuard transactions." If the MCP tools are loaded correctly, Cursor will call the UpGuard tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "upguard-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Cursor

The MCP Server allows your AI client to call tools like `list_user_risks` directly into the context. The agent then writes working code that incorporates the live risk data, meaning you don't have to switch out of your editor.

The server touches records from `list_identity_breaches`. This means the AI can write code that handles lists of breached identities, letting you build immediate checks into your application logic.

You use `get_vendor` and then chain the results through `list_vendor_risks`. This sequence lets the AI client write code that accepts a vendor name parameter and returns a list of associated risks.

Yes. The tool `list_user_risks` provides current user risk data, letting your AI client write code that validates permissions or flags accounts based on the returned risk level.

The server touches vendor details, account risks, user risk data, and lists of monitored domains/IPs. The AI client can access this granular information directly within your coding environment.

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