How to Use the Moodle MCP in Vercel AI SDK

Q: How do I configure the Moodle MCP Server with Vercel AI SDK?

First, install the packages using npm install ai @ai-sdk/mcp in your project directory. Then, initialize the connection using createMCPClient with your Vinkius endpoint token and pass the tools directly into streamText. Always call mcpClient.close() when your streaming sequence finishes.

Q: Can I stream Moodle course contents using Vercel AI SDK?

Yes, you can use getcoursecontents to fetch syllabus details and stream them live. The Vercel AI SDK handles the UI rendering while the MCP Server fetches the data from your LMS. This prevents the browser from freezing during large data transfers.

Q: What is the best way to handle student grade lookups in React?

Use the getusergrades tool inside your Next.js API route to fetch student records. The Vercel AI SDK streams the grades directly to your React hooks, rendering the data as it arrives. You avoid writing complex polling logic on the client side.

Build real-time Next.js dashboards that stream Moodle course data directly to students using 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 Moodle MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Moodle course updates live in React

The `get_course_contents` tool fetches course modules and outputs them directly to your Next.js frontend. By hooking this MCP Server up to Vercel's streaming protocol, your React components render syllabus items instantly as the LLM processes them. You don't make users stare at a blank loading screen while the database compiles the response. This setup works perfectly inside Edge Functions where cold starts kill performance. Your code calls `mcpClient.tools()` to grab the active endpoints, feeds them to `streamText`, and lets the Vercel AI SDK handle the UI updates. It's a direct connection from your Moodle database to the user's viewport without slow middleware.

Real-time grade tracking without page refreshes

The `get_user_grades` tool pulls gradebook records immediately into your web application. When your AI client executes this command, the Vercel AI SDK streams the raw grade data directly into your custom student dashboard. Students watch their performance metrics populate in real time, bypassing the slow Moodle web interface entirely. You write clean TypeScript that connects the server using `createMCPClient`. Once the data streams through, remember to call `mcpClient.close()` to free up the Vercel Edge runtime resources. This keeps your serverless execution fast and prevents database pool exhaustion during exam season.

Instant student onboarding via this MCP Server

The `create_users` tool registers new accounts on your LMS directly from custom sign-up pages. Using this MCP Server, your Vercel AI SDK app can instantly spin up a student profile and immediately execute `enrol_users` to drop them into their assigned classes. Your entire onboarding sequence runs inside a single edge request, keeping signup friction low. This approach completely replaces legacy backend cron jobs that run batch imports every hour. You get immediate verification, meaning students gain access to their course materials the exact second they finish registering. It turns a sluggish administrative process into an instant, satisfying onboarding loop.

Setup guide

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

First, install the packages using `npm install ai @ai-sdk/mcp` in your project directory. Then, initialize the connection using `createMCPClient` with your Vinkius endpoint token and pass the tools directly into `streamText`. Always call `mcpClient.close()` when your streaming sequence finishes.

Yes, you can use `get_course_contents` to fetch syllabus details and stream them live. The Vercel AI SDK handles the UI rendering while the MCP Server fetches the data from your LMS. This prevents the browser from freezing during large data transfers.

The server runs on Vinkius's V8 Isolate Sandbox, which responds in milliseconds. This speed prevents your Vercel Edge Functions from hitting their execution limits when calling `list_courses` or `get_enrolled_users`. Your runtime stays lightweight and fast.

Use the `get_user_grades` tool inside your Next.js API route to fetch student records. The Vercel AI SDK streams the grades directly to your React hooks, rendering the data as it arrives. You avoid writing complex polling logic on the client side.

Your Moodle passwords and student email addresses never touch Vercel's public edge logs. Vinkius manages the authentication token securely in an ephemeral sandbox, passing only the requested user records back to your SDK application.

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