How to Use the Logto (Auth Platform) MCP in Vercel AI SDK

Q: How do I connect the Logto (Auth Platform) MCP server to my Vercel AI SDK project?

Install @ai-sdk/mcp and ai. Configure your server URL in createMCPClient and pass mcpClient.tools() to generateText or streamText. Remember to call mcpClient.close() once your stream finishes to prevent memory leaks in Edge Functions.

Q: Can my Vercel AI SDK agent manage Logto (Auth Platform) organization memberships?

Yes, your agent handles membership updates by invoking listorganizationusers and modifying user records. You write the prompt, and the SDK streams the updated membership list straight to your React components.

Q: How does this Logto (Auth Platform) MCP server handle user password updates in Vercel AI SDK?

The server exposes updatemyaccountpassword and verifypassword directly to your agent. Your Vercel AI SDK client calls these tools sequentially, collecting the required password verification ID and applying the change in a single streaming interaction.

Q: Does this setup support Logto's API resource configuration?

Yes. Your agent can execute createresource and listresources to register new API targets. This allows you to build admin consoles where the AI configures OAuth scopes and resource identifiers dynamically.

Build live-streaming auth dashboards where your Vercel AI SDK client updates Logto configurations in real time.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Logto (Auth Platform) MCP to Vercel AI SDK

Create your Vinkius account to connect Logto (Auth Platform) 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 Logto (Auth Platform) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live User Provisioning and Updates

Use `create_user` to instantly provision new accounts inside your Logto tenant. Your AI client calls this tool along with `update_user` to sync user metadata directly from conversational prompts. The Vercel AI SDK streams these updates straight to your frontend UI, showing the raw status changes without forcing a page refresh. You don't have to write custom API routes for basic profile management. When users ask your agent to modify their profile, the agent executes `update_my_account_profile` and `update_my_account_primary_email` in the background. The UI updates instantly as the stream resolves, keeping the user interface in lockstep with the identity provider.

Multi-tenant organization setup with Vercel AI SDK

Use `create_organization` to spin up new isolated customer environments on the fly. Your agent runs this alongside `create_role` to establish baseline permissions for the new workspace. It bypasses manual setup scripts entirely by letting the AI handle tenant onboarding. As your Vercel AI SDK client loops through the setup, it streams the configuration progress directly to the browser. It reads current setups using `list_organizations` and immediately displays the newly created tenants in your UI. This keeps your React or Next.js layout reactive while background auth operations execute.

Active Security and MFA Enforcement

Use `verify_user_password` to challenge users before executing sensitive identity changes. This MCP server lets your agent handle verification flows directly. When a user requests an MFA change, the agent initiates security checks with `send_verification_code` and checks active factors using `list_mfa_verifications`. The agent manages the entire security loop by executing `bind_mfa_verification` or `remove_mfa_verification` based on the user's input. Since the Vercel AI SDK handles streaming responses, the user sees step-by-step verification prompts in the chat window, preventing jarring redirects during high-security actions.

Setup guide

Set up Logto (Auth Platform) 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 Logto (Auth Platform) 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 Logto (Auth Platform) 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 Logto. 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 Logto (Auth Platform) 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 Logto (Auth Platform) MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and `ai`. Configure your server URL in `createMCPClient` and pass `mcpClient.tools()` to `generateText` or `streamText`. Remember to call `mcpClient.close()` once your stream finishes to prevent memory leaks in Edge Functions.

Yes, your agent handles membership updates by invoking `list_organization_users` and modifying user records. You write the prompt, and the SDK streams the updated membership list straight to your React components.

The server exposes `update_my_account_password` and `verify_password` directly to your agent. Your Vercel AI SDK client calls these tools sequentially, collecting the required password verification ID and applying the change in a single streaming interaction.

Yes. Your agent can execute `create_resource` and `list_resources` to register new API targets. This allows you to build admin consoles where the AI configures OAuth scopes and resource identifiers dynamically.

All sensitive credentials, user profiles, and MFA secrets remain inside your secure V8 sandbox. This MCP server acts as a direct pipe, meaning your Logto passwords and verification codes never touch external third-party logging systems.

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