How to Use the Markdown Utilities Engine MCP in Vercel AI SDK

Q: How do I install the Markdown Utilities Engine in my Vercel AI SDK project?

Run npm install ai @ai-sdk/mcp in your terminal. Then, configure createMCPClient with the HTTP transport pointing to your Vinkius endpoint and pass the tools directly into your streamText call.

Q: How does the Markdown Utilities Engine handle TOC anchors when paired with Vercel AI SDK?

The generatetoc tool creates standard slugged anchors for your headers. Your Next.js router handles these hash links natively, letting users jump to specific document sections without full page reloads.

Q: Do I need to keep the connection to the MCP Server open indefinitely?

No, you should close it. Always call mcpClient.close() after your Vercel AI SDK generation finishes to prevent hanging connections in serverless environments.

Format perfect Markdown tables and TOCs live in your Next.js frontend 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 Markdown Utilities Engine MCP to Vercel AI SDK

Create your Vinkius account to connect Markdown Utilities Engine 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 Markdown Utilities Engine with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream JSON arrays into clean tables with Vercel AI SDK

The `generate_table_from_json` tool extracts headers and formats rows directly inside your edge-rendered UI. Instead of waiting for a slow backend process to finish, your users watch the formatted Markdown table render row-by-row as the Vercel AI SDK handles the stream. By offloading the table construction to this MCP Server, your streaming assistant outputs structured JSON that instantly converts to clean Markdown on the fly. This setup eliminates broken table layouts in your React or Next.js components.

Generate broken-link-free TOCs in your UI components

The `generate_toc` tool parses raw Markdown text and returns a bulleted list of anchor links pointing to exact header slugs. When building a documentation viewer using the Vercel AI SDK, this ensures users get functional navigation sidebars that match their content perfectly. You don't need to write custom regex parsers or run heavy post-processing scripts on the client side. The tool handles the heavy lifting, allowing your Next.js application to display interactive tables of contents immediately after the text streams in.

Run deterministic Markdown tools on Vercel Edge Functions

This MCP Server connects to your edge runtime using `createMCPClient` to keep your serverless functions fast and lightweight. You grab the tools with `mcpClient.tools()` and feed them directly into `streamText` without adding heavy parsing libraries to your deployment bundle. After the processing completes, you call `mcpClient.close()` to clean up the HTTP connection. This keeps your edge execution times minimal while guaranteeing that every generated table and list remains perfectly formatted.

Setup guide

Set up Markdown Utilities Engine 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 Markdown Utilities Engine 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 Markdown Utilities Engine 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 markdown-utilities. 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 Markdown Utilities Engine 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 Markdown Utilities Engine MCP in Vercel AI SDK

Run `npm install ai @ai-sdk/mcp` in your terminal. Then, configure `createMCPClient` with the HTTP transport pointing to your Vinkius endpoint and pass the tools directly into your `streamText` call.

Yes, you can. The Vercel AI SDK streams the structured Markdown generated by `generate_table_from_json` block-by-block, allowing your UI components to render the table dynamically as it arrives.

The `generate_toc` tool creates standard slugged anchors for your headers. Your Next.js router handles these hash links natively, letting users jump to specific document sections without full page reloads.

No, you should close it. Always call `mcpClient.close()` after your Vercel AI SDK generation finishes to prevent hanging connections in serverless environments.

Vinkius processes your raw Markdown text and JSON arrays in an ephemeral V8 sandbox. No data is stored or logged after the `generate_toc` or `generate_table_from_json` tools finish execution.

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