How to Use the 42Crunch MCP in Vercel AI SDK

Q: How do I use 42Crunch with the Vercel AI SDK to show an API's security score?

Have your agent call the getapi tool with the API's ID. You can then stream the securityscore field from the response directly into a React or Svelte component. It's a single tool call to get the most important metric.

Q: Can I build a CI dashboard with 42Crunch and the Vercel AI SDK?

Yes. You can build a frontend that lets your agent importapi on a new commit, triggeraudit, and then use getauditreport to stream the results into a live dashboard. Your whole team can see the security posture of every build as it happens.

Q: What's the setup for the 42Crunch MCP Server and the Vercel AI SDK?

It's straightforward. Just npm install ai @ai-sdk/mcp, then use createMCPClient and point it to your Vinkius URL. The client will discover the 42Crunch tools, and you can pass them to generateText or streamText.

Stream 42Crunch API security reports directly into your React components with the Vercel AI SDK. No more loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect 42Crunch MCP to Vercel AI SDK

Create your Vinkius account to connect 42Crunch 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 42Crunch with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage API Collections in Your UI

This MCP server gives your AI client direct control over your 42Crunch API collections. You can build a simple dashboard that uses `list_collections` and `list_apis` to show everything you're protecting. The Vercel AI SDK streams the results, so your UI populates in real time as the data arrives. From that same UI, you can let users add or remove APIs. A button click can have your agent call `import_api` with a new OpenAPI spec or `delete_api` to remove an old one. The changes happen instantly without a full page reload, making for a much better user experience.

Trigger Scans from Your Frontend

Let developers trigger security audits right from their workspace. Your agent, powered by the Vercel AI SDK, can expose the `trigger_audit` tool. A developer working on an API can click a button in your app to kick off a fresh static security audit on their latest spec. After an audit starts, you don't have to leave the user guessing. Your agent can periodically call `list_scans` to check the status. You can stream these status updates directly into your UI, showing progress as it happens. It turns a background task into a live, observable event.

Live Security Reports with this MCP Server

Getting the results is just as easy. Once a scan or audit is complete, your agent can use `get_audit_report` or `get_scan_report` to pull the detailed findings. You get a structured object back, ready to be displayed. Here's the cool part for frontends: you can stream the report. First, call `get_api` to instantly show the overall security score. Then, as the larger `get_audit_report` data streams in, you can progressively render the detailed vulnerabilities and recommendations in your components. It feels incredibly responsive.

Setup guide

Set up 42Crunch 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 42Crunch 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 42Crunch 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 42Crunch. 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 42Crunch 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 42Crunch MCP in Vercel AI SDK

Have your agent call the `get_api` tool with the API's ID. You can then stream the `security_score` field from the response directly into a React or Svelte component. It's a single tool call to get the most important metric.

Yes. You can build a frontend that lets your agent `import_api` on a new commit, `trigger_audit`, and then use `get_audit_report` to stream the results into a live dashboard. Your whole team can see the security posture of every build as it happens.

It's straightforward. Just `npm install ai @ai-sdk/mcp`, then use `createMCPClient` and point it to your Vinkius URL. The client will discover the 42Crunch tools, and you can pass them to `generateText` or `streamText`.

The MCP server handles the auth and gives your agent a standard set of tools. You don't write custom fetch requests or install a separate SDK for 42Crunch. Your agent just knows how to `trigger_audit` because it's a standard tool, saving you a ton of boilerplate code.

Yes. Your OpenAPI specification is sent through an encrypted, single-use Vinkius sandbox for processing. The MCP Server uses the spec to run the audit and immediately discards it after the operation. Your data is never stored at rest on the Vinkius platform.

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