How to Use the Pennylane MCP in Vercel AI SDK

Q: How do I configure the Pennylane MCP Server inside a Next.js project using Vercel AI SDK?

Initialize the client using createMCPClient with an HTTP transport pointing to your Vinkius endpoint. Pass the tools from mcpClient.tools() into streamText to let your LLM query French ledgers. Remember to call mcpClient.close() when the edge function finishes executing.

Q: Can I stream Pennylane product catalogs to React components?

Yes, you feed listproducts directly into the Vercel AI SDK tool call handler. The SDK streams the raw product list, allowing your frontend to render custom UI cards for each item before the full payload even finishes downloading.

Q: Does the Vercel AI SDK support OAuth for this Pennylane MCP toolset?

Yes, you configure the authProvider option when initializing your HTTP transport. This lets your Next.js app pass user-specific tokens to Pennylane securely, keeping individual French accounting ledgers isolated.

Pipe Pennylane customer invoices and estimates directly into your Next.js app in real-time 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 Pennylane MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Real-Time Invoice Streaming

`list_customer_invoices` feeds raw invoice records directly into your Vercel AI SDK streaming component. Your users watch their French VAT breakdowns, totals, and invoice statuses render on-screen piece by piece instead of staring at a blank loading screen. This setup takes raw JSON from Pennylane and maps it straight to React components. By using this MCP Server with `get_customer_invoice_details`, you bypass manual state management and let your agent populate your billing UI dynamically.

Instant Customer Profiles in Vercel AI SDK

`get_customer_details` fetches full French account profiles to render customer-facing dashboards on the edge. The Vercel AI SDK handles the asynchronous data fetching, passing the structured Pennylane payload straight to your UI template. You can pair this with `list_customers` to build searchable directories that load instantly in Next.js. The agent handles the search logic, queries the MCP endpoint, and streams the matching client records without cold-start delays.

Dynamic Estimate Generation

`create_customer` registers new accounts in your Pennylane directory directly from a user-facing chat input. The Vercel AI SDK parses the user's plain-text message, structures the payload, and executes the creation call in a single turn. Once the customer exists, the agent can call `list_estimates` to show pending quotes. This converts manual back-office tasks into a fast, interactive chat interface running on Edge Functions.

Setup guide

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

Initialize the client using `createMCPClient` with an HTTP transport pointing to your Vinkius endpoint. Pass the tools from `mcpClient.tools()` into `streamText` to let your LLM query French ledgers. Remember to call `mcpClient.close()` when the edge function finishes executing.

Yes, you feed `list_products` directly into the Vercel AI SDK tool call handler. The SDK streams the raw product list, allowing your frontend to render custom UI cards for each item before the full payload even finishes downloading.

Yes, you configure the `authProvider` option when initializing your HTTP transport. This lets your Next.js app pass user-specific tokens to Pennylane securely, keeping individual French accounting ledgers isolated.

You should implement caching at the Vercel Edge layer or wrap `list_customer_invoices` in a React SWR hook. This prevents your users from triggering redundant API calls to Pennylane during active chat sessions.

Your Pennylane invoice details, customer records, and supplier transactions are processed inside isolated V8 sandboxes. Vercel AI SDK never stores your French accounting data; it only streams the encrypted payload directly from Vinkius to your client browser.

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