How to Use the Frontegg MCP in Vercel AI SDK

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

Install the @ai-sdk/mcp package and initialize it with createMCPClient. Point the HTTP transport URL to your running Frontegg instance. Then pass the tools method into your stream call.

Build live identity management dashboards in React using the Vercel AI SDK to stream Frontegg user provisioning right to the browser.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Frontegg MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Vercel AI SDK streaming for tenants

When your agent calls `create_tenant`, the Vercel AI SDK streams the resulting tenant ID directly into your Next.js frontend without a loading state. Your UI reacts instantly as the backend spins up the new workspace. You can chain this right into user creation. The agent fires `create_user` to assign the first admin, and the success state renders on the client side immediately. It beats polling a database or making the user stare at a spinner while identity services sync.

Read and display user metadata

Support dashboards need real-time data from `get_user_details` to be useful. Connecting this MCP Server lets your conversational UI pull up active accounts on demand. A user types a request, and your application hits the endpoint to fetch their exact status and role assignment. The results pipe straight into your React components. If you need to audit access levels, the agent grabs the data via `list_system_roles` and `list_permissions`. The raw JSON transforms into a readable table in your app while the generative text is still typing out the summary.

Handle destructive actions with immediate feedback

Offboarding requires precision, so when an admin asks to wipe an account, your agent executes `delete_tenant` or `delete_user` and pushes the confirmation back to the client UI. There is no ambiguity about whether the API call succeeded. You handle the connection through `createMCPClient` in your server action. Once the tool executes, the frontend updates the active user list by running `list_users` again. The interface stays perfectly in sync with your actual Frontegg environment.

Setup guide

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

Install the `@ai-sdk/mcp` package and initialize it with `createMCPClient`. Point the HTTP transport URL to your running Frontegg instance. Then pass the tools method into your stream call.

Yes. When the agent triggers the user provisioning tool, the SDK streams the tool call and result back to the frontend. Your React components update the moment the new user ID exists.

The MCP Server handles the actual API auth with Frontegg. Your Vercel AI SDK application just needs the endpoint token to talk to the server itself. You configure this in your transport settings.

The server returns an error from the environment status tool. The SDK catches this and streams an error state to your UI, letting you prompt the user to check their API keys.

It accesses your tenant identifiers, user metadata, and M2M tokens. The server acts as a pass-through sandbox and does not store your permissions or system roles permanently. Everything stays in memory just long enough to execute the request.

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