How to Use the Formstack MCP in Vercel AI SDK

Q: How do I connect Formstack to the Vercel AI SDK?

Use createMCPClient with your Vinkius endpoint. Pass the transport object, call mcpClient.tools(), and feed the resulting array into streamText.

Q: Can the Vercel AI SDK modify live Formstack configurations?

Yes. Your agent can execute updateform to change settings or deleteform to remove outdated surveys. Just ensure your OAuth scopes allow write access.

Q: How do I display raw Formstack HTML using Vercel AI SDK?

Ask your agent to run getformhtml. It pulls the unstyled markup, which the LLM can then stream into your React application for custom rendering.

Q: What happens to submission data privacy when using the Formstack MCP Server?

All PII pulled via getsubmissiondetails runs through the V8 Isolate Sandbox. The Vinkius environment is ephemeral, meaning no user responses or form metadata linger after the HTTP connection closes.

Build dynamic form experiences in React and Next.js by connecting the Vercel AI SDK to Formstack.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Formstack MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Render Formstack MCP Server Data Live

Your Next.js app doesn't need to wait for a backend cron job to pull form data. You can wire `list_forms` directly into the Vercel AI SDK and stream the results straight to the DOM. Users see available surveys appear in real-time. When a client requests specific survey details, your agent executes `get_form_details` and `list_form_fields`. The UI updates instantly with the exact structure required. No loading spinners, just raw data populating components as the LLM processes it.

Stream Form Submissions to Frontends

Fetching user responses usually means building custom API routes. Instead, pass `list_submissions` to `streamText` and let the agent handle the heavy lifting. The AI pulls the latest entries and formats them into your dashboard on the fly. If a user needs deeper context on a specific entry, the model calls `get_submission_details`. It grabs the precise answers and pipes them into your React components. You get a live, conversational interface for your form data without writing custom fetch logic.

Automate Webhook Management

Setting up event triggers manually wastes time. Your AI client can manage this dynamically by running `list_form_webhooks` to check current configurations. If a specific endpoint is missing, the model knows immediately. From there, the agent triggers `create_webhook` to point Formstack events at your Vercel edge functions. You build intelligent systems that adapt their own data pipelines based on user commands.

Setup guide

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

Use `createMCPClient` with your Vinkius endpoint. Pass the transport object, call `mcpClient.tools()`, and feed the resulting array into `streamText`.

Yes. Your agent can execute `update_form` to change settings or `delete_form` to remove outdated surveys. Just ensure your OAuth scopes allow write access.

The LLM output streams directly to your frontend, but the MCP Server handles the actual API calls synchronously. You see the text generation happen live while the tools fetch `get_form_stats` in the background.

Ask your agent to run `get_form_html`. It pulls the unstyled markup, which the LLM can then stream into your React application for custom rendering.

All PII pulled via `get_submission_details` runs through the V8 Isolate Sandbox. The Vinkius environment is ephemeral, meaning no user responses or form metadata linger after the HTTP connection closes.

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