How to Use the EdApp MCP in Vercel AI SDK

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

First, install the @ai-sdk/mcp package. Then, create a client pointing to your Vinkius endpoint URL and pass the tools from mcpClient.tools() into the streamText function. It's designed for a quick setup.

Q: Can I stream EdApp user progress reports with the Vercel AI SDK?

Yes. Your agent can call getcourseprogressreport and the Vercel AI SDK streams the results directly into your UI components. This is perfect for building live dashboards where users see progress bars fill in real time.

Stream EdApp training data directly into your React and Next.js UIs. Build live dashboards with 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 EdApp MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Learner Dashboards

Your agent can use `list_learners` and `get_learner_details` to populate a live dashboard of everyone in your training program. With the Vercel AI SDK, this data streams directly into your UI components. You're not showing a loading spinner; your users are watching the list build in real time. Take it a step further by tracking progress. Have your agent call `get_course_progress_report` and `get_lesson_attempts_log` for a specific user. The results stream back, letting you update charts and progress bars on the fly. It makes your admin panel feel incredibly fast and interactive.

Real-Time Course Catalogs

Build a course browser that feels alive. Your AI client can call `list_training_courses` and `list_course_collections` to get all available training content from EdApp. Instead of waiting for a full API response, the Vercel AI SDK streams the course titles one by one into your interface. When a user clicks on a course, the AI can instantly call `list_course_lessons` to fetch its contents. Streaming the lesson list makes the application feel responsive, as if there's no network latency at all. This is how you build a front-end experience that stands out.

On-the-Fly Admin with your MCP Server

Give your L&D managers a conversational interface to manage EdApp. They can ask the AI to "add a new learner named Jane Doe" and your agent will execute the `create_new_learner` tool. The confirmation appears in the chat UI instantly. This works for cleanup, too. An admin could ask to "find inactive users from Q1." Your agent uses `list_learners` to get the data, identifies the right accounts, and presents them. With a confirmation, it calls `remove_learner` for each one. All the back-and-forth happens naturally through your UI.

Setup guide

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

First, install the `@ai-sdk/mcp` package. Then, create a client pointing to your Vinkius endpoint URL and pass the tools from `mcpClient.tools()` into the `streamText` function. It's designed for a quick setup.

Yes. Your agent can call `get_course_progress_report` and the Vercel AI SDK streams the results directly into your UI components. This is perfect for building live dashboards where users see progress bars fill in real time.

Absolutely. You can build an interface that lets admins conversationally add users with `create_new_learner` or remove them with `remove_learner`. The results are streamed back to your UI for immediate feedback.

Think live admin dashboards, dynamic course catalogs, or conversational bots for managing training. It's a great fit for any application where seeing data appear instantly improves the user experience.

Your connection is authenticated with a unique Vinkius endpoint token. The MCP server runs in an ephemeral, sandboxed V8 isolate and only processes the specific learner and course data requested by tools like `get_learner_details`. All data is transmitted over HTTPS and nothing is stored.

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