How to Use the Apiary MCP in Vercel AI SDK

Q: Can Apiary triggers run tests in Vercel AI SDK?

You use runtests to execute Dredd-style checks. The results stream back to your client, showing your team exactly which endpoints failed.

Pull API blueprints into your Vercel AI SDK interface and render real-time documentation updates for your users.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Apiary MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Apiary blueprints into your Vercel AI SDK app

Feed `get_api` results directly into your React or Svelte components. Your end users see live API source code without waiting for background tasks to finish. This MCP server connects your UI to raw design data. You stop manually syncing documentation files and let your AI client handle the heavy lifting.

Automate documentation updates via AI SDK

Push your latest Markdown or Swagger changes using `publish_blueprint`. The update triggers instantly, keeping your Vercel-hosted docs in sync with your codebase. Your agents handle the deployment logic between your repository and the platform. You get immediate feedback on whether the push succeeded or hit a validation error.

Check mock server status in your frontend

Use `get_doc_url` to grab live mock endpoints for your front-end testing. You display these links right in your dashboard so developers can verify integrations on the fly. Stop digging through web portals for connection strings. Your AI client fetches the exact URL your team needs to begin development.

Setup guide

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

Install the MCP client packages and pass your endpoint into `createMCPClient`. You then inject the tools into your `streamText` function to start querying your API projects.

Yes, the transport layer is built for this. You handle your API requests within the edge runtime without blocking your main process.

You use `run_tests` to execute Dredd-style checks. The results stream back to your client, showing your team exactly which endpoints failed.

We keep your API blueprints and team identifiers private. Your AI client only sees the specific data you request through the tool interface.

No. You use an ephemeral endpoint token for the session. Your credentials never touch the client code directly.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.