How to Use the Vanta MCP in Vercel AI SDK

Q: How can I check Vanta's overall compliance posture using the AI SDK?

You call vantacompliancestatus. It returns the full compliance dashboard, including pass rates and critical alerts. Because it streams live via your AI client, you show this data to users instantly in their browser.

Q: Can I see failing tests in Vanta using the AI SDK?

Yep. You can use vantalisttests to get all monitoring controls for SOC 2, ISO 27001, HIPAA, and GDPR. The streaming result lets you display which specific test failed or is warning right on the screen.

Q: What if I need to check employee training status in Vanta using the AI SDK?

Use vantalistpeople to get all personnel data. This list includes security training completion, device compliance details, and access review status for everyone.

Q: Does the Vanta MCP Server help with risk management? (Vanta and AI SDK)

Absolutely. You can use vantalistrisks to pull the entire risk register. This provides impact scores, likelihood levels, assigned controls, and mitigation statuses directly into your UI.

Show compliance data live in the UI with Vanta and the AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Vanta MCP to Vercel AI SDK

Create your Vinkius account to connect Vanta to Vercel AI 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 Vanta with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time Compliance Dashboard

Your user needs to know if you're ready for an audit. Use `vanta_compliance_status` to get a dashboard showing pass rates per framework, critical alerts, and the readiness score across SOC 2, ISO 27001, HIPAA, and GDPR. Because this streams directly into your React component, your user sees the numbers appear live—no loading spinner required. This makes building high-trust, interactive UIs simple.

Check Device Health on Demand

Need to audit endpoints? Call `vanta_list_computers` and get a list of monitored devices. You'll see the OS version, encryption status, antivirus presence, and compliance state for every machine. Since this data streams, your UI can update instantly when fetching device inventory or flagging non-compliant machines before an audit.

Track Audit Evidence Status

Don't get blindsided by missing paperwork. Use `vanta_list_evidence_requests` to list outstanding evidence needs—like screenshots and documents needed from team members, along with their due dates. Showing this request status in real-time via the AI SDK gives your app a critical operational view, letting users know exactly who needs to submit what.

Setup guide

Set up Vanta MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Vanta tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Vanta transactions",
});

console.log(text);
await mcpClient.close();

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 Vanta. 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 Vanta 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 Vanta MCP in Vercel AI SDK

You call `vanta_compliance_status`. It returns the full compliance dashboard, including pass rates and critical alerts. Because it streams live via your AI client, you show this data to users instantly in their browser.

This MCP Server touches compliance status metrics across multiple frameworks (SOC 2, ISO 27001, HIPAA, GDPR). The results are read-only dashboards and lists of records.

Yep. You can use `vanta_list_tests` to get all monitoring controls for SOC 2, ISO 27001, HIPAA, and GDPR. The streaming result lets you display which specific test failed or is warning right on the screen.

Use `vanta_list_people` to get all personnel data. This list includes security training completion, device compliance details, and access review status for everyone.

Absolutely. You can use `vanta_list_risks` to pull the entire risk register. This provides impact scores, likelihood levels, assigned controls, and mitigation statuses directly into your UI.

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