How to Use the Paycove MCP in Vercel AI SDK

Q: How do I configure Vercel AI SDK to call Paycove tools via the MCP Server?

Install the packages using npm install ai @ai-sdk/mcp and set up createMCPClient pointing to your Vinkius endpoint. Pass the tools directly into generateText or streamText so your agent can execute actions like createquote or listpayments. Remember to call mcpClient.close() when the session ends to prevent memory leaks in serverless environments.

Q: How does the Vercel AI SDK handle Paycove client authentication?

The SDK uses the authProvider configuration inside createMCPClient to pass OAuth tokens. This ensures your agent safely runs getclient or listinvoices using the active user's specific billing permissions.

Stream Paycove billing operations and real-time invoice states directly into your Next.js frontend using Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Paycove MCP to Vercel AI SDK

Create your Vinkius account to connect Paycove to Vercel AI SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Paycove with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Render live invoice updates in your Vercel AI SDK app

Stop making your users wait for page refreshes when generating billing documents. This MCP Server lets your AI client run `create_invoice` and stream the resulting payment status directly into your React components. Your users see the invoice details populate on their screen as the API processes the transaction. You don't have to build complex loading states or polling mechanisms. By calling `mcpClient.tools()` and feeding them to `streamText`, the interface updates dynamically as the backend updates. When a rep requests a bill, the system fetches details via `get_invoice` and renders the data instantly.

Convert quotes to invoices inside Edge Functions

Heavy server-side rendering hurts conversion rates. This integration runs inside Edge Functions, letting your agent run `convert_quote_to_invoice` without cold starts or regional latency. The Vercel AI SDK handles the lightweight streaming connection while Paycove executes the CPQ transition. It keeps your frontend highly responsive even during high-traffic sales cycles. Your agent can instantly run `get_quote` to verify pricing, swap the state, and render the final invoice block without blocking the main UI thread.

Real-time client lookups in Next.js sidebars

Sales reps need client history while drafting pitches. Let your agent search your accounts using `list_clients` and `get_client` to render profile cards right in your workspace sidebar. You just initialize the connection with `createMCPClient` and pass the tools to your chat interface. The agent pulls the exact record, displays the history, and you shut down the connection with `mcpClient.close()` to keep your serverless execution times low.

Setup guide

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

Install the packages using `npm install ai @ai-sdk/mcp` and set up `createMCPClient` pointing to your Vinkius endpoint. Pass the tools directly into `generateText` or `streamText` so your agent can execute actions like `create_quote` or `list_payments`. Remember to call `mcpClient.close()` when the session ends to prevent memory leaks in serverless environments.

Yes. When the user requests a billing change, Vercel AI SDK streams the execution of `create_invoice` or `convert_quote_to_invoice` directly to your UI. The component updates in real-time as the server receives the payload, eliminating loading spinners.

The SDK uses the `authProvider` configuration inside `createMCPClient` to pass OAuth tokens. This ensures your agent safely runs `get_client` or `list_invoices` using the active user's specific billing permissions.

Absolutely. The server runs on Vinkius, and the Vercel AI SDK client connects via lightweight HTTP transport. This setup allows your agent to run `list_overdue_invoices` or `list_products` from Edge routes without hitting node-specific API limitations.

All invoice and client payloads are transmitted over encrypted TLS directly to Vinkius. Your actual Paycove API keys never touch the client browser, as the SDK handles the secure token handshake on the server side during tools execution.

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