How to Use the Lunatask MCP in Vercel AI SDK

Q: How do I connect Lunatask to my Vercel AI SDK project?

Install the required @ai-sdk/mcp package and initialize the client using createMCPClient with your HTTP endpoint URL. Pass the tools directly into generateText or streamText to let your agent start managing tasks. Always call the close method on the client when the session ends to prevent memory leaks.

Q: Why does the Lunatask MCP Server require an area ID to create tasks?

The createnewtask tool requires both a name and an areaid to keep your workspace organized. This ensures new tasks are filed in the correct category right away, avoiding unorganized clutter in your inbox.

Stream Lunatask metadata updates directly into your Next.js or React frontend using the Vercel AI SDK and this secure MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lunatask MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream real-time habit updates in Vercel AI SDK

Your users don't want to stare at loading spinners while their habit trackers update. When you hook this MCP Server to your frontend, habit completions render instantly as they happen. The `track_habit_completion` tool updates the database and pushes the state change to your UI components without delay. This means you build interfaces where habit streaks animate the millisecond the background task finishes. You don't have to write custom polling logic or manage complex state synchronization. The client handles the streaming state, while the server takes care of the API handshake.

Secure task metadata management

Privacy isn't an afterthought here. Because Lunatask uses zero-knowledge encryption, tools like `list_tasks_metadata` and `get_task_metadata` only return structural records, not your raw, sensitive task names. Your AI client organizes workflows using IDs and timestamps, keeping your actual task content completely private. When you need to modify a record, use `update_existing_task` or `delete_task` by targeting these specific IDs. The Vercel AI SDK coordinates these operations behind the scenes, letting your interface reflect structural updates while keeping the plaintext content safely locked on the user's local device.

Direct journal and task creation

Creating records requires zero round-trips through intermediary backend servers. Your agent can execute `create_new_task` or `create_journal_entry` directly from the edge. The server processes the payload and returns the structural metadata to your app in real-time. This setup works perfectly inside Edge Functions with the MCP architecture, bypassing heavy node runtimes. Frontend code stays light, fast, and highly responsive. You get a direct pipeline from the user's prompt to their secure productivity vault.

Setup guide

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

Install the required `@ai-sdk/mcp` package and initialize the client using `createMCPClient` with your HTTP endpoint URL. Pass the tools directly into `generateText` or `streamText` to let your agent start managing tasks. Always call the close method on the client when the session ends to prevent memory leaks.

No, it cannot. Due to zero-knowledge encryption constraints, `list_tasks_metadata` only returns IDs, areas, and timestamps. Your raw task names and notes are never exposed to the API or the LLM during listing operations.

The server operates on encrypted metadata only, meaning it does not need access to your local private keys to list tasks or verify habits. Plaintext payloads are only generated locally when creating entries or tasks, maintaining your privacy boundary.

The `create_new_task` tool requires both a name and an `area_id` to keep your workspace organized. This ensures new tasks are filed in the correct category right away, avoiding unorganized clutter in your inbox.

Absolutely, because this server only touches encrypted metadata and structural IDs. Your actual journal text and task names never pass through the network in plaintext. The local sandbox environment ensures that your sensitive data remains zero-knowledge and fully encrypted.

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