How to Use the Checkmarx MCP in Vercel AI SDK

Q: How do I connect the Checkmarx MCP Server to Vercel AI SDK?

Run npm install ai @ai-sdk/mcp. Then use createMCPClient with your HTTP endpoint and pass the resulting tools into streamText or generateText.

Q: Can Vercel AI SDK stream Checkmarx scan details?

Yes. Your agent calls getscandetails to check SAST and KICS execution timings. The framework streams that engine-specific failure data right to your frontend.

Q: Does the Checkmarx MCP Server support OAuth?

You can pass an authProvider to the client configuration. This handles the token exchange before your agent accesses any security data.

Q: How do I list active MCP scans in Vercel AI SDK?

Call listscans through your agent's tool access. It returns completed, running, and failed jobs along with their target branches.

Build live AppSec dashboards in React by streaming Checkmarx MCP Server vulnerability data directly to users through 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 Checkmarx MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Checkmarx MCP Server Findings

`get_scan_results` pulls confirmed flaws and exact line numbers straight into your Next.js frontend. You don't have to wait for a massive JSON payload to finish downloading. The Vercel AI SDK streams those security states right to the user's screen as the agent parses them. Your UI updates instantly. When a developer needs the exact rule ID, `list_bfl` streams the Best Fix Location directly into your custom React component.

Trigger Scans from the Edge

`run_scan` kicks off a new Checkmarx One code scan the moment a user asks for a security check. You hook this up to a chat interface, and the agent handles the API calls behind the scenes. If the user pushes another commit while the job runs, `cancel_scan` drops the old context. That stops engine resource waste immediately.

Live Infrastructure Audits

`get_kics_results` focuses entirely on Terraform, CloudFormation, and Kubernetes YAML misconfigurations. Your dashboard renders these infrastructure flaws live while the user types their query. To track where these live, `list_projects` maps the codebase. Then `list_applications` groups them into overarching risk reports for logical product visibility.

Setup guide

Set up Checkmarx 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 Checkmarx 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 Checkmarx 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 Checkmarx. 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 Checkmarx 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 Checkmarx MCP in Vercel AI SDK

Run `npm install ai @ai-sdk/mcp`. Then use `createMCPClient` with your HTTP endpoint and pass the resulting tools into `streamText` or `generateText`.

Yes. Your agent calls `get_scan_details` to check SAST and KICS execution timings. The framework streams that engine-specific failure data right to your frontend.

You can pass an `authProvider` to the client configuration. This handles the token exchange before your agent accesses any security data.

Call `list_scans` through your agent's tool access. It returns completed, running, and failed jobs along with their target branches.

This server handles exact source code vulnerability locations and infrastructure misconfigurations. Vinkius isolates this execution inside an ephemeral V8 sandbox that burns down after the request, leaving zero persistent traces of your Terraform flaws.

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