How to Use the Contrast Security MCP in Vercel AI SDK

Q: How do I set up the Contrast Security MCP Server with Vercel AI SDK?

Run npm install ai @ai-sdk/mcp to get started. Instantiate the connection with createMCPClient pointing to your Vinkius URL, then pass the tools directly into your streamText function. Remember to call mcpClient.close() when the session ends.

Q: What is the best way to render critical vulnerabilities?

Use listcriticalvulnerabilities inside your streaming loop to catch high-risk issues early. The Vercel AI SDK UI components can map the returned JSON array to visual alert badges as the data streams in.

Stream Contrast Security vulnerability alerts directly into your Next.js UI in real-time with the Vercel 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 Contrast Security MCP to Vercel AI SDK

Create your Vinkius account to connect Contrast Security 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 Contrast Security with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live Contrast Security alerts inside Vercel AI SDK

Stop making users wait for heavy security reports to load. This MCP integration lets you pull active vulnerability data using `list_critical_vulnerabilities` and stream the raw findings straight to your UI. Your frontend receives the security status block-by-block, keeping the interface snappy and interactive while your agent parses the threat level. You can trigger detailed trace lookups instantly. When a user clicks a streamed alert, your application calls `get_vulnerability_details` behind the scenes. Because this runs on Vercel's edge network, security teams get instant diagnostics without server-side lag.

Build interactive security dashboards with Vercel AI SDK

Give your developers a conversational interface to query their application posture. By mounting the MCP Server, your LLM uses `search_applications_by_name` to find target environments. The agent then lists active agents on those nodes via `list_monitored_servers` without leaving the chat window. Users can drill down into specific code flaws. Your code calls `get_application_details` to present the exact metadata of the vulnerability. The Vercel AI SDK renders these complex JSON payloads into clean, readable UI components on the fly.

Run instant compliance checks using this MCP Server

Automate your access control reviews directly inside your internal admin tools. The agent uses `list_organization_users` to pull the active user roster from your Contrast dashboard. It matches names against your internal database to flag unauthorized access. You can verify organization-wide security settings in one go. The `get_organization_info` tool fetches your current subscription limits and security policies. It takes less than five lines of TypeScript to feed this data directly into your streaming dashboard.

Setup guide

Set up Contrast Security 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 Contrast Security 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 Contrast Security 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 Contrast Security. 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 Contrast Security 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 Contrast Security MCP in Vercel AI SDK

Run `npm install ai @ai-sdk/mcp` to get started. Instantiate the connection with `createMCPClient` pointing to your Vinkius URL, then pass the tools directly into your `streamText` function. Remember to call `mcpClient.close()` when the session ends.

Yes, this setup is built for the edge. You connect to the hosted Vinkius endpoint via HTTP transport, meaning no heavy dependencies block your cold starts. Your agent quickly pulls vulnerability data using `list_vulnerability_traces` with minimal latency.

Vinkius manages the core credentials, but you can pass dynamic user tokens using the SDK's `authProvider`. This ensures that tools like `search_vulnerabilities` only show data the active developer is authorized to see.

Use `list_critical_vulnerabilities` inside your streaming loop to catch high-risk issues early. The Vercel AI SDK UI components can map the returned JSON array to visual alert badges as the data streams in.

Your source code never leaves your secure environment. This integration only reads vulnerability metadata and application names through `get_vulnerability_details`. All data transmission goes through Vinkius's isolated sandbox, ensuring zero-trust execution.

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