How to Use the ChargeOver MCP in Vercel AI SDK

Q: How do I connect the ChargeOver MCP Server to Vercel AI SDK?

Install @ai-sdk/mcp and initialize it with createMCPClient. You pass the Vinkius HTTP transport URL into the configuration. Call mcpClient.tools() and feed that into your streamText function.

Q: What happens when I close the ChargeOver connection in Vercel AI SDK?

You must call mcpClient.close() after your text generation finishes. This terminates the HTTP transport and cleans up memory. Failing to close the connection leads to memory leaks in serverless environments.

Stream ChargeOver billing data directly into your Next.js frontend 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 ChargeOver MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream ChargeOver Subscriptions Live

The `list_billing_subscriptions` tool pulls active customer packages directly from your billing system. Your Vercel AI SDK implementation streams this data straight to the user interface as the edge function executes. You avoid building custom webhooks or polling loops to check payment statuses. Calling `get_customer_details` fetches specific account histories while the generation runs. React components render the output instantly, showing users their exact billing standing without loading spinners.

Render Invoices in Your UI

Using `list_chargeover_invoices` gives your Vercel AI SDK application immediate access to billing histories. Next.js server actions call the tool and pipe the JSON response directly into your frontend components. Users see their payment records appear character by character. The `get_invoice_details` endpoint grabs specific line items and totals. You connect this to your chat interface so customers can ask about specific charges and get verified answers immediately.

Vercel AI SDK MCP Server Integration

Fetching payment records requires the `list_billing_transactions` tool to read raw financial events. This MCP Server connects to your Vercel AI SDK setup via a simple HTTP transport configuration. You pass the tools into `streamText` and let the language model decide when to check the ledger. Finding sales proposals happens through `list_billing_quotes`. Edge functions handle the request, retrieve the pricing data, and format it for the client. The entire process stays within your existing serverless infrastructure.

Setup guide

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

Install `@ai-sdk/mcp` and initialize it with `createMCPClient`. You pass the Vinkius HTTP transport URL into the configuration. Call `mcpClient.tools()` and feed that into your `streamText` function.

Yes, the SDK streams tool execution results natively. When the agent calls `get_invoice_details`, the resulting JSON pipes directly to your frontend components. Users watch the billing data render in real-time.

Edge runtime support is built directly into the Vercel AI SDK. You configure the MCP client inside your route handler. The HTTP transport fetches billing data without requiring a Node.js backend.

You must call `mcpClient.close()` after your text generation finishes. This terminates the HTTP transport and cleans up memory. Failing to close the connection leads to memory leaks in serverless environments.

The Vinkius V8 Isolate Sandbox processes your raw transaction logs and invoice line items in ephemeral memory. Nothing writes to disk during the execution. Authentication uses a single endpoint token that expires immediately after the session ends.

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