How to Use the Ellie Planner MCP in Vercel AI SDK

Q: How do I fetch specific task details?

Use gettask with the unique task identifier. The SDK retrieves the full payload, including dates and labels, so your UI components can render the detailed editor modal instantly.

Build live-updating project boards that render Ellie Planner tasks directly in your Next.js UI 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 Ellie Planner MCP to Vercel AI SDK

Create your Vinkius account to connect Ellie Planner 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 Ellie Planner with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time task rendering in your Next.js UI

`list_tasks` pulls active items from your workspace so your application can render them instantly on the client side. By streaming these results directly into your React components, users see their schedule update without waiting for a full page reload. This approach removes the typical loading spinner lag. Your interface displays the current plan immediately, making the user experience feel like a native desktop app instead of a sluggish web portal.

Instant task creation via this MCP Server

`create_task` lets your application add new items to a user's schedule with optional dates and labels. Because the Vercel AI SDK handles tool execution on the edge, the new item appears in the UI the millisecond your agent decides to run the tool. You don't need to write custom backend handlers or state synchronization logic. The SDK coordinates the payload directly with the Vercel-hosted MCP Server endpoint, keeping your local state clean.

Dynamic metadata updates on the edge

`update_task` modifies existing items to keep your interface in sync with user changes. The Vercel AI SDK processes these modifications inside Edge Functions, bypassing heavy server cold starts to maintain a snappy interface. When a user drags a task card to a new date, the system executes the update instantly. The visual timeline reflects the change immediately, ensuring the UI always matches the actual planning board.

Setup guide

Set up Ellie Planner 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 Ellie Planner 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 Ellie Planner 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 Ellie Planner. 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 Ellie Planner 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 Ellie Planner MCP in Vercel AI SDK

Use the authProvider option in createMCPClient to manage OAuth tokens. This lets your web app securely read lists using `list_lists` on behalf of each signed-in user.

Yes. Call mcpClient.tools() within your Server Action and pass them to streamText. You can immediately call `complete_task` or update schedules while streaming the UI response.

Always call mcpClient.close() inside your clean-up functions or at the end of your edge execution path. This prevents open connections to the MCP Server from hanging and consuming unnecessary serverless runtime.

Use `get_task` with the unique task identifier. The SDK retrieves the full payload, including dates and labels, so your UI components can render the detailed editor modal instantly.

Your task titles, due dates, and list names remain inside the secure Vinkius V8 sandbox. We never store your planning data, and it only travels directly between your Next.js application and the secure API endpoint.

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