How to Use the Authing MCP in Vercel AI SDK

Q: How do I map Authing roles to Vercel AI SDK users?

Call listroles and listgroups to pull current permissions. You then inject those roles into your state management to control what parts of the UI a specific user sees.

Stream Authing identity data directly into your Vercel AI SDK frontends for real-time user management.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Authing MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time user data for Vercel AI SDK

Feed live account details into your UI components using `get_user`. You stop waiting for spinners and show profiles the instant the agent fetches them. Your interface reacts to identity changes as they happen. It pushes data straight through your streaming pipeline without lag.

Manage Authing security from your code

Trigger `get_security_settings` to adjust pool configurations on the fly. You control the environment settings directly from your application logic. This MCP Server keeps your frontend synced with your backend. You handle identity updates without writing custom API middleware.

Audit your Authing logs in the browser

Pull security records with `get_audit_logs` to show activity history in your dashboard. Your users see exactly when and where logins occurred. It turns raw security data into readable events for your app. You display the trail of activity while keeping the logic inside your SDK flow.

Setup guide

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

Use the authProvider configuration inside your client initialization. It passes your credentials safely to the server so the connection stays private. You don't need to expose keys in your browser code.

Yes. The transport layer is built for low-latency environments. It connects to the server endpoint and executes your identity commands within the edge runtime.

Vinkius manages the sandbox with a zero-trust policy. Your identity records, like user IDs and audit logs, never touch public storage. Everything happens inside an ephemeral memory space.

The tools stream results directly into your response flow. You get the data as it arrives, keeping your UI responsive. No blocking calls are required.

Call `list_roles` and `list_groups` to pull current permissions. You then inject those roles into your state management to control what parts of the UI a specific user sees.

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