How to Use the Expensya MCP in Vercel AI SDK

Q: How do I install the Expensya MCP Server in my Vercel AI SDK project?

Run npm install ai @ai-sdk/mcp to get started. Initialize the client using createMCPClient with your Vinkius HTTP endpoint, and pass the tools directly to your text generation functions.

Q: Can I stream Expensya expense reports live using Vercel AI SDK?

Yes, you can. By calling listexpensereports within your Next.js streamText function, your application renders active expense folders as they are retrieved from the API, giving users immediate feedback.

Q: How does the Expensya integration handle user authentication in Vercel AI SDK?

Use the authProvider configuration inside createMCPClient to handle OAuth tokens. This MCP connection lets you securely call getauthenticateduserprofile to verify the active user's identity on the edge.

Q: What is the correct way to close the MCP client after fetching payment methods?

Always call mcpClient.close() after your Vercel AI SDK stream finishes. This releases the connection pool used to fetch data from listpaymentmethods and keeps your serverless functions lightweight.

Render real-time Expensya expense creation and live reports directly inside your React UI 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 Expensya MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Vercel AI SDK Expense Creation

`create_new_expense` lets your React frontend render expense creation steps in real-time as the user speaks or types. Your Vercel AI SDK setup calls the MCP server to parse receipt details and instantly display the pending transaction. Users watch their Expensya receipt data populate live in your Next.js app instead of staring at a blank loading spinner. You hook `createMCPClient` to your edge functions, stream the tool outputs, and close the connection with `mcpClient.close()` once the expense is saved.

Real-time Currency and Category Validation

`list_supported_currencies` and `list_expense_categories` provide the exact parameters your Next.js frontend needs to validate inputs before submission. The Vercel AI SDK streams these allowed options directly into your custom dropdown components. This direct streaming ensures users only select active Expensya categories like Meals or Travel. Running this check on Vercel's edge network prevents API failures and keeps your interface snappy.

Dynamic Project and Tag Selection

`list_analytical_projects` pulls active corporate tracking codes directly into the user's active Next.js chat session. When your Vercel AI SDK agent suggests tags via `list_expense_tags`, the UI updates instantly to show matching items. Developers configure this by feeding `mcpClient.tools()` into `streamText` to let the model select the correct Expensya project code on the fly. This eliminates the need for hardcoded dropdowns or stale local state.

Setup guide

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

Run `npm install ai @ai-sdk/mcp` to get started. Initialize the client using `createMCPClient` with your Vinkius HTTP endpoint, and pass the tools directly to your text generation functions.

Yes, you can. By calling `list_expense_reports` within your Next.js `streamText` function, your application renders active expense folders as they are retrieved from the API, giving users immediate feedback.

Use the `authProvider` configuration inside `createMCPClient` to handle OAuth tokens. This MCP connection lets you securely call `get_authenticated_user_profile` to verify the active user's identity on the edge.

Always call `mcpClient.close()` after your Vercel AI SDK stream finishes. This releases the connection pool used to fetch data from `list_payment_methods` and keeps your serverless functions lightweight.

All communications with the Expensya API go through Vinkius's secure sandboxed environment. Your database credentials and financial records are never exposed to the LLM; the model only receives the structured JSON payloads returned by specific tools.

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