How to Use the Indy MCP in Vercel AI SDK

Q: How do I stream Indy form creation into a Next.js app using the Vercel AI SDK?

You initialize the connection using the createMCPClient helper from the SDK's MCP package. Pass the Vinkius HTTP endpoint to the transport, then feed the tools directly into streamText so your agent can execute createform and render the output live.

Q: How does the Vercel AI SDK handle authentication for Indy tools?

You pass your Vinkius credentials through the authProvider configuration when setting up your client. This secures tools like getaccountinfo and ensures your users only access their own freelance data.

Q: How does this setup protect my Indy form submissions and user data?

All form submissions retrieved via listrecords and user profiles from listusers are processed within Vinkius's isolated sandbox. No raw customer database files are stored on Vercel, keeping your private client contacts and agency metrics safe.

Get real-time freelance lead data streaming directly into your Next.js UI with the Indy MCP Server and 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 Indy MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Live Indy Client Intake Forms in Vercel AI SDK

The `list_forms` and `create_form` tools allow your UI to pull and build client intake forms on the fly. When your user asks to build a new intake questionnaire, the Vercel AI SDK streams the form structure directly into your React component without waiting for a full server roundtrip. Here's the thing: clients see fields appearing instantly as the model configures them. You can also call `get_form` to fetch existing layouts and display them immediately. Because this Indy MCP Server works natively with edge functions, your users get zero-latency updates when editing their onboarding questionnaires.

Real-Time Submission Tracking Without Spinners

The `list_records` and `get_record` tools let you watch incoming client submissions as they hit your database. Instead of making users refresh a dashboard, your Vercel AI SDK setup streams new lead records straight to their screen. The moment a prospect submits a form, the details render in real time. This setup bypasses the usual API lag. By hooking these MCP tools directly into your streaming UI components, you build a live activity feed that keeps freelancers updated on active leads without writing custom polling logic.

Instant Webhook Routing for Edge Workflows

The `create_webhook` and `delete_webhook` tools manage automated event triggers for your client lifecycle. You can configure active alerts directly from your streaming chat interface, letting your agent set up HTTP endpoints instantly. The Vercel AI SDK coordinates these tools to link Indy events with your custom edge routes. When a contract gets signed or a form is filled, your application reacts immediately, using `list_webhooks` to ensure your active endpoints remain perfectly in sync.

Setup guide

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

You initialize the connection using the `createMCPClient` helper from the SDK's MCP package. Pass the Vinkius HTTP endpoint to the transport, then feed the tools directly into `streamText` so your agent can execute `create_form` and render the output live.

Yes. The underlying server runs on Vinkius, meaning your edge functions only need to make lightweight HTTP requests to trigger tools like `list_records` or `get_user` without heavy dependencies.

You pass your Vinkius credentials through the `authProvider` configuration when setting up your client. This secures tools like `get_account_info` and ensures your users only access their own freelance data.

The SDK handles errors gracefully by catching exceptions on tools like `delete_webhook` over the MCP connection. You can write custom UI fallbacks to alert the user if a webhook deletion fails, keeping your interface clean.

All form submissions retrieved via `list_records` and user profiles from `list_users` are processed within Vinkius's isolated sandbox. No raw customer database files are stored on Vercel, keeping your private client contacts and agency metrics safe.

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