How to Use the Typefully MCP in Vercel AI SDK

Q: Can I list drafts using Typefully and the Vercel AI SDK?

Yep. You call listdrafts via the client. The tool returns all your current content draft titles, which you can then process in real-time on your React or Next.js UI.

Q: What data does Typefully touch when using the Vercel AI SDK?

This server primarily touches user profile data (getuserprofile) and content drafts (the text in createdraft or updatedraft). This is all handled via streaming tokens.

Q: Does Typefully support scheduling with the Vercel AI SDK?

It does. You run the schedulecontent tool, and your agent handles passing that scheduled content data through the streamable UI element.

Q: Is listing social accounts possible with Typefully and the Vercel AI SDK?

You can list connected accounts using listsocialaccounts. The result comes back as a stream, perfect for showing the user exactly what services are active.

Streamline your content workflow with Typefully and 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 Typefully MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Drafting & Content Management

You can start by creating fresh material using `create_draft`. The agent manages all draft versions, letting you see them listed with `list_drafts`. Need to tweak something? You'll use `update_draft` for minor changes or `get_draft_details` if you need the full text. It’s fast enough that the user sees these results streaming directly into the UI.

Publishing Content Live

To get content out right now, just call `publish_immediately`. This handles sending your finished work to social accounts. Want to check what networks you're connected to? Running `list_social_accounts` shows the list of accessible platforms. It’s simple data appearing in real-time—no loading screen drama.

Scheduling and Profile Info

Don't post everything at once; use `schedule_content` to set future publishing dates. This tool handles the back end of your content calendar. Plus, you can pull basic data about yourself with `get_user_profile`. The result streams in as text, making it look like the AI is thinking out loud right on the screen.

Setup guide

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

The Vercel AI SDK lets your agent call Typefully tools and stream the results directly to your frontend. This means users see data appear instantly, instead of waiting for a big loading spinner.

Yep. You call `list_drafts` via the client. The tool returns all your current content draft titles, which you can then process in real-time on your React or Next.js UI.

This server primarily touches user profile data (`get_user_profile`) and content drafts (the text in `create_draft` or `update_draft`). This is all handled via streaming tokens.

It does. You run the `schedule_content` tool, and your agent handles passing that scheduled content data through the streamable UI element.

You can list connected accounts using `list_social_accounts`. The result comes back as a stream, perfect for showing the user exactly what services are active.

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