How to Use the edX MCP in Vercel AI SDK

Q: How do I configure edX course search inside a Vercel AI SDK project?

Install @ai-sdk/mcp and instantiate the client using createMCPClient with your Vinkius endpoint. Pass the tools directly into streamText and let your agent call searchcourses to pull live academic data.

Q: How does Vercel AI SDK handle edX course run updates?

Your agent uses getcourserun to check specific dates and run states. The SDK streams the raw status directly to the client UI, updating the enrollment status instantly without requiring a page refresh.

Q: How is my user search data protected when using this MCP Server?

Every request sent to searchcourses or getsubjects runs in an ephemeral, zero-trust V8 sandbox. Vinkius never stores your users' search queries, course selections, or program IDs after the execution lifecycle ends.

Stream edX course details directly into your React components in real-time using 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 edX MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build real-time edX search with Vercel AI SDK

The `search_courses` tool identifies courses based on free-text queries, subject filters, and difficulty levels, feeding the raw JSON directly to your Vercel AI SDK stream. This setup bypasses intermediate API mapping layers, letting your agent fetch live matches from MIT or Harvard and render them instantly on the frontend. By combining this search function with Vercel's streaming UI components, your users watch course options materialize as they type. You avoid the lag of traditional API gateways because the MCP Server runs in a secure sandbox close to your edge functions.

Live course metadata rendering via this MCP Server

The `get_course` tool retrieves precise syllabus info, pacing details, and estimated effort parameters for any course key your agent extracts from the conversation. Your Vercel AI SDK application processes this structured data on the fly, rendering custom UI cards without waiting for a full page reload. This direct execution model means your agent can immediately query `get_course_runs` to check if a specific Harvard computer science course is starting next week. The end user gets up-to-the-minute enrollment options without your backend having to poll the edX APIs.

Direct program structure extraction via MCP

The `get_program` tool checks the architecture of MicroMasters, Professional Certificates, and XSeries tracks directly from the edX catalog. Your Vercel AI SDK application maps these multi-course tracks into visual timelines, presenting educational pathways to the user as the agent explains them. To refine these pathways, the agent uses `get_subjects` to align the program's focus with the user's specific learning goals. Because the Vinkius platform handles the API authorization, your edge functions require zero extra API keys to fetch this data.

Setup guide

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

Install `@ai-sdk/mcp` and instantiate the client using `createMCPClient` with your Vinkius endpoint. Pass the tools directly into `streamText` and let your agent call `search_courses` to pull live academic data.

Yes. Because this MCP Server runs on Vinkius's V8 Isolate Sandbox, the `search_programs` tool returns results in milliseconds. The Vercel AI SDK streams these program details chunk-by-chunk directly into your frontend components.

Your agent uses `get_course_run` to check specific dates and run states. The SDK streams the raw status directly to the client UI, updating the enrollment status instantly without requiring a page refresh.

No. Vinkius manages all upstream partner credentials on its secure servers. Your Vercel AI SDK application only needs a single endpoint token to execute any tool in this catalog.

Every request sent to `search_courses` or `get_subjects` runs in an ephemeral, zero-trust V8 sandbox. Vinkius never stores your users' search queries, course selections, or program IDs after the execution lifecycle ends.

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