How to Use the Medium MCP in Vercel AI SDK

Q: How do I connect the Medium MCP Server to my Vercel AI SDK app?

Install the MCP client package and call createMCPClient pointing to your endpoint. Pass the client tools directly into streamText and close the connection when done.

Q: Does Vercel AI SDK support real-time rendering of Medium publication lists?

Yes, you can call listpublications inside your streaming UI component. This lets your users see their available publications load dynamically as they draft their posts.

Stream raw draft data directly into Next.js pages 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 Medium MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Push Medium drafts straight from your Vercel AI SDK UI

This MCP Server exposes `create_draft` to let your Vercel AI SDK application stream newly generated stories directly into a React editor component. The model streams the markdown text, and the moment your user clicks approve, the SDK pushes the draft to Medium without any page refreshes. You do not need to manage complex state or write custom API routes to handle the writing flow. By calling `get_my_user_id` inside a Next.js Edge Route, your Vercel AI SDK app immediately routes the streaming output to the correct author profile.

Control Medium publications via Vercel AI SDK

The `create_publication_post` tool lets your Vercel AI SDK application publish stories directly to specific brand publications in real-time. Your Next.js interface calls `list_my_publications` to populate a live dropdown menu, letting authors choose their target publication before the AI client starts streaming content. When your Vercel AI SDK frontend handles the routing, managing multi-author blogs becomes straightforward. The `list_contributors` tool lets your app verify contributor permissions on the fly, ensuring only authorized writers can submit drafts to your corporate Medium publications.

Fetch profile details for custom author portals

The `get_my_profile` tool fetches the active writer's details to populate your Vercel AI SDK dashboard instantly. Instead of making users manually input their bio or profile picture, your Next.js application displays this data directly from their linked Medium account. This MCP integration simplifies setup by letting the model check credentials via `get_authenticated_user` on the first load. Authors see their actual Medium stats and avatar immediately inside your Vercel AI SDK workspace, making the editor feel like a cohesive extension of the platform itself.

Setup guide

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

Install the MCP client package and call `createMCPClient` pointing to your endpoint. Pass the client tools directly into `streamText` and close the connection when done.

No, the API does not support scheduling directly. You must use `create_draft` to generate the post and then schedule it manually through the platform's dashboard.

Yes, you can call `list_publications` inside your streaming UI component. This lets your users see their available publications load dynamically as they draft their posts.

The API requires hosted image URLs in the markdown content. Your Vercel AI SDK application should upload the image to an external bucket first, then insert that URL into the body parameters for `create_post`.

Your integration token is stored securely as an environment variable on Vercel's edge network. The server processes draft content and profile data in ephemeral memory, ensuring credentials never leak to the client browser.

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