How to Use the iFax MCP in Vercel AI SDK

Q: How do I set up the iFax MCP Server with Vercel AI SDK?

Install @ai-sdk/mcp and call createMCPClient with the Vinkius HTTP URL. This connects your edge function to the MCP server. Don't forget to call mcpClient.close() when the edge function finishes.

Q: How does iFax error handling work in a Vercel AI SDK stream?

If sendfax fails, the error returns inside the tool call block. Your agent reads the error, alerts the user, and can automatically invoke resendfax to try again.

Send and track faxes live in your Next.js frontend by streaming real-time status updates 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 iFax MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Fax Statuses Live in Vercel AI SDK Frontends

The `get_fax_status` tool lets your agent check ongoing delivery progress and stream updates directly to your users. Instead of forcing users to stare at a loading spinner, your Next.js app renders real-time transmission stages as they happen. Your app calls `list_faxes` to show a live history log. Because this MCP server runs on Vercel's Edge network, your UI stays fast while handling heavy document metadata.

Transmit PDF Documents Directly from Edge Functions

The `send_fax` tool handles file metadata and base64 content so your agent can transmit documents instantly. You pass the payload directly from your React form to the Vercel AI SDK client without writing custom API backends. If a transmission fails, the AI triggers `resend_fax` instantly. That's how your frontend users get immediate feedback without waiting for manual page refreshes.

Download and View Received Documents in Real-Time

The `download_fax` tool pulls incoming documents directly into your user-facing interface. Your application displays the downloaded file contents the moment the Vercel AI SDK receives the payload. Users can also trigger `cancel_fax` directly from their browser if they spot an error. This keeps your interface responsive and saves your team from wasting money on accidental transmissions.

Setup guide

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

Install `@ai-sdk/mcp` and call `createMCPClient` with the Vinkius HTTP URL. This connects your edge function to the MCP server. Don't forget to call `mcpClient.close()` when the edge function finishes.

Yes. Your LLM constructs the base64 string and passes it directly to the `send_fax` tool. The SDK handles the streaming response so your UI updates the moment the upload completes.

If `send_fax` fails, the error returns inside the tool call block. Your agent reads the error, alerts the user, and can automatically invoke `resend_fax` to try again.

No. This MCP server communicates with a cloud API, meaning you send and receive documents without physical phone lines or paper.

Your document payloads and recipient phone numbers pass through Vinkius's zero-trust V8 Isolate Sandbox. This ensures no files are cached on external servers during transmission, keeping your sensitive medical or legal documents isolated and secure.

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