How to Use the BasicOps MCP in Vercel AI SDK

Q: Can Vercel AI SDK stream BasicOps task updates to the browser?

Yes. When the model invokes updatetask, the tool execution state streams to the client automatically. Your UI can show the exact moment the task status changes.

Stream BasicOps project updates and task details directly into your Next.js frontend using 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 BasicOps MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream projects with the BasicOps MCP Server

Your users hate loading spinners. When you connect this MCP Server to your Vercel AI SDK backend, project lists render instantly in your React components. The AI client calls `list_projects` and streams the JSON chunks straight to the browser. Fetching deeper context works exactly the same way. A user clicks a project, and your system triggers `list_project_sections` followed by `list_project_tasks`. The UI populates task by task as the model processes the response.

Build live task creation interfaces

Text inputs become action triggers. Your end user types a request to assign a new deliverable, and the Vercel AI SDK parses that intent into a `create_task` tool call. The response streams back confirming the new ID and assignment. Edits happen just as fast. The model can hit `update_task` to change deadlines or statuses based on chat input. You just pass the tool execution results back to the stream handler to keep the conversation moving.

Surface team conversations instantly

Project context usually lives buried in chat threads. By mapping `list_task_messages` to your interface, you expose those critical discussions right next to the work. The frontend pulls these logs without forcing the user to switch tabs. Adding user context is a single function call away. You run `list_team_users` or `get_account_info` to grab profile details, feeding exact names and IDs into your prompt. The agent knows exactly who is responsible for what.

Setup guide

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

Install @ai-sdk/mcp and set up an HTTP transport endpoint. Call createMCPClient with your Vinkius URL, then pass mcpClient.tools() into your generateText or streamText call.

Yes. When the model invokes update_task, the tool execution state streams to the client automatically. Your UI can show the exact moment the task status changes.

Vinkius manages the underlying OAuth or API key connection. Your backend just passes a single endpoint token through the transport configuration.

The HTTP transport layer works perfectly on Vercel Edge Functions or Cloudflare Workers. You don't need a persistent Node.js server to run get_project or list_webhooks.

It only reads messages your Vinkius connection has permission to see. The list_task_messages tool pulls specific thread contents, so you should scope your access tokens strictly to the projects your app actually needs.

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