How to Use the Formbricks MCP in Vercel AI SDK

Q: How do I install the Formbricks MCP Server for Vercel AI SDK?

Run npm install ai @ai-sdk/mcp. You use createMCPClient with your HTTP transport URL. Pass the tools to generateText and remember to call mcpClient.close() when finished.

Q: Does the Formbricks integration support OAuth in Vercel AI SDK?

The setup supports authProvider for OAuth. You pass the token in your transport config to authenticate against the API.

Q: How do I filter feedback data?

You pass a specific survey ID into listresponses. The model filters the data before streaming the text back to your UI.

Build live feedback loops in your React apps with the Formbricks Vercel AI SDK integration.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Formbricks MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Streaming UI with the MCP Server

The `create_survey` tool builds new feedback modals on the fly based on user chat context. You hook this up to your Next.js frontend. The AI decides a user is frustrated, calls the tool, and the survey streams directly into the UI without a page reload. That means no loading spinners. You pull active campaigns using `list_surveys` and feed them into the chat window. The end user gets a native experience while the AI handles the API calls in the background.

Context-Aware Micro-Surveys

You need context before prompting a user, so the `get_person` tool fetches their specific profile data. The Vercel AI SDK streams this context back to your agent. If the user hasn't hit a key milestone, you don't bother them. Look, timing is everything with micro-surveys. By checking `list_action_classes`, your agent knows exactly which events fire in your app via MCP. It triggers the right question exactly when the user finishes a task.

Live Response Feeds

Your admin dashboards can render live feedback by hitting `list_responses` through the MCP connection. The AI SDK streams the raw text straight into your Svelte or Vue components. You spot a bad rating instantly. The agent then pulls the full context with `get_response`. It formats the data, streams it to the support team's view, and highlights exactly why the user dropped off.

Setup guide

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

Run `npm install ai @ai-sdk/mcp`. You use `createMCPClient` with your HTTP transport URL. Pass the tools to `generateText` and remember to call `mcpClient.close()` when finished.

Yes. The AI calls the creation tools and the result streams straight to the frontend. Your users see the feedback form appear instantly.

The setup supports `authProvider` for OAuth. You pass the token in your transport config to authenticate against the API.

You pass a specific survey ID into `list_responses`. The model filters the data before streaming the text back to your UI.

This server handles raw user feedback and profile identifiers via the `get_person` endpoint. You control exactly which HTTP endpoint token your client uses. The isolated sandbox ensures strict boundaries between your internal user data and the external model.

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