How to Use the DoiT MCP in Vercel AI SDK

Q: How do I stream DoiT billing summaries with Vercel AI SDK?

You call getbillingcostsummary within the Vercel AI SDK tool parameter block to fetch DoiT data. The Vercel AI SDK receives the raw DoiT JSON payload and streams the parsed financial figures directly to your frontend components.

Q: How does DoiT handle multi-cloud accounts in Vercel AI SDK?

The listconnectedcloudaccounts tool returns your entire AWS, GCP, and Azure organization structure from DoiT directly to the Vercel AI SDK. Reading this DoiT list allows your Vercel AI SDK agent to group cost metrics by cloud provider dynamically.

Q: What happens when a DoiT budget is exceeded in Vercel AI SDK?

The listexceededcostbudgets tool identifies the broken thresholds inside DoiT and alerts the Vercel AI SDK instantly. By receiving this DoiT data, your Vercel AI SDK application can trigger instant UI warnings or automated Slack notifications.

Feed live DoiT cloud cost alerts and asset details directly into your web interface 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 DoiT MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed Real-Time DoiT Spikes to Vercel AI SDK

The `list_critical_cost_spikes` tool lets your Vercel AI SDK agent pull active, high-severity budget overruns from DoiT instantly. Because this MCP Server integrates with Vercel's streaming architecture, these DoiT alerts render in the browser as they occur without waiting for a full API response block to resolve. You get immediate visibility into active spikes through DoiT's `list_cost_anomalies` mapped directly to Vercel AI SDK UI components. Your Vercel AI SDK frontend displays the exact DoiT-monitored cloud resources bleeding cash before the user even has time to click a manual refresh button.

Inspect Multi-Cloud Assets with Vercel AI SDK

The `search_cloud_assets` tool queries your AWS, GCP, and Azure inventory inside DoiT using simple keyword matches initiated by the Vercel AI SDK. It runs directly inside Vercel Edge Functions, keeping latency low and rendering DoiT asset profiles dynamically in the browser. Once your Vercel AI SDK agent finds the target, it triggers DoiT's `get_asset_details` to fetch configuration specs and raw costs. The user sees a complete breakdown of their DoiT cloud setup without leaving your Vercel application's viewport.

Render Live DoiT Budget Status on Your Frontend

The `list_exceeded_cost_budgets` tool pulls a list of all DoiT cloud budgets currently over their limits directly into your Vercel AI SDK application. Your typescript agent uses this MCP Server to map DoiT budget data directly to Vercel AI SDK UI components, showing users exactly which team exceeded their spend. Combining this with `list_cost_budgets` allows you to build interactive DoiT financial dashboards inside your Vercel AI SDK project. The Vercel AI SDK handles the data fetching, and your React layout displays the DoiT progress bars in real-time.

Setup guide

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

You call `get_billing_cost_summary` within the Vercel AI SDK tool parameter block to fetch DoiT data. The Vercel AI SDK receives the raw DoiT JSON payload and streams the parsed financial figures directly to your frontend components.

Yes, this MCP Server works with Vercel Edge Functions to search DoiT assets. Your Vercel AI SDK agent executes `search_cloud_assets` on the edge to retrieve matching multi-cloud resources from DoiT without cold starts.

The `list_connected_cloud_accounts` tool returns your entire AWS, GCP, and Azure organization structure from DoiT directly to the Vercel AI SDK. Reading this DoiT list allows your Vercel AI SDK agent to group cost metrics by cloud provider dynamically.

The `list_exceeded_cost_budgets` tool identifies the broken thresholds inside DoiT and alerts the Vercel AI SDK instantly. By receiving this DoiT data, your Vercel AI SDK application can trigger instant UI warnings or automated Slack notifications.

Security is handled at the network boundary between DoiT and your Vercel AI SDK application. This MCP Server only reads your DoiT cloud asset metadata and historical billing records, never touching raw application data or database credentials. Vinkius runs the endpoint in a zero-trust sandbox, protecting your DoiT API keys from Vercel AI SDK frontend exposure.

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