How to Use the Amazing Marvin MCP in Vercel AI SDK

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

Install @ai-sdk/mcp and initialize the client with your Vinkius endpoint. Pass the tools from mcpClient.tools() directly into streamText to let your agent manage tasks.

Q: Does the Vercel AI SDK support live time tracking with Amazing Marvin?

It does. You call starttracking inside your tool definition, and the SDK streams the active timer state back to your UI components instantly.

Q: How do I modify existing tasks using this integration?

Use the updatetask tool. Your agent modifies titles, changes scheduled dates, or marks items as done, then sends the updated payload back to your app.

Pipe your Amazing Marvin tasks and time logs straight into live React components 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 Amazing Marvin MCP to Vercel AI SDK

Create your Vinkius account to connect Amazing Marvin 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 Amazing Marvin with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Task Creation via the Vercel AI SDK

The `add_task` tool inserts new tasks directly into your Amazing Marvin database, letting your users build schedules without waiting for API roundtrips. Your AI client calls this tool to write tasks, categories, and scheduled dates behind the scenes. Because this runs on an MCP Server hosted by Vinkius, your frontend receives the raw JSON stream instantly. You bypass the typical loading spinners by feeding the tool output directly into your application's state.

Real-Time Tracking in React Components

The `start_tracking` and `stop_tracking` tools control the active timer inside your Amazing Marvin account. This lets you build a custom dashboard where users toggle their work sessions using plain English commands. Your agent initiates the timer on Vinkius V8 isolates via MCP, which keeps execution times under 10 milliseconds. The live status streams down to the client immediately, updating your UI progress bars in real time.

Dynamic Hierarchy Browsing on the Edge

The `get_children` tool retrieves the nested structure of your categories and projects. Your application uses this tool to let users dig into their Marvin folders using natural language. You configure the client using `createMCPClient` inside your Next.js edge route. This setup handles the data fetch quickly, keeping your database credentials secure while serving the nested tree to the user.

Setup guide

Set up Amazing Marvin 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 Amazing Marvin 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 Amazing Marvin 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 Amazing Marvin. 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 Amazing Marvin 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 Amazing Marvin MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and initialize the client with your Vinkius endpoint. Pass the tools from `mcpClient.tools()` directly into `streamText` to let your agent manage tasks.

Yes, this MCP Server runs on Vinkius's V8 sandboxes which play nicely with edge runtimes. You fetch task lists with `get_today_items` without hitting cold starts.

It does. You call `start_tracking` inside your tool definition, and the SDK streams the active timer state back to your UI components instantly.

Use the `update_task` tool. Your agent modifies titles, changes scheduled dates, or marks items as done, then sends the updated payload back to your app.

Vinkius runs this MCP Server in an ephemeral sandbox, meaning your tasks, projects, and time-tracking logs are never stored on our servers. Your API tokens are encrypted and used only to authorize direct requests to Marvin.

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