How to Use the BoxyHQ (Enterprise SSO) MCP in Vercel AI SDK

Q: How do I configure BoxyHQ (Enterprise SSO) inside a Vercel AI SDK project using an MCP Server?

Install @ai-sdk/mcp and initialize the client using the Vinkius HTTP endpoint. Pass the tools directly into streamText and let your agent call addconnection or getconnections as needed. Keep in mind you must call mcpClient.close() once the generation finishes to prevent hanging connections.

Q: How does a Vercel AI SDK agent handle SCIM group sync with BoxyHQ (Enterprise SSO)?

Your agent uses getdirectorygroups to fetch the group structure from the identity provider. It then parses the JSON payload to map enterprise groups to your local application roles on the fly.

Spin up SAML and SCIM connections on the fly and stream the configuration status straight to your Vercel AI SDK interface.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BoxyHQ (Enterprise SSO) MCP to Vercel AI SDK

Create your Vinkius account to connect BoxyHQ (Enterprise SSO) 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 BoxyHQ (Enterprise SSO) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live SSO Provisioning with Vercel AI SDK

The `add_connection` tool registers SAML or OIDC configurations directly from user prompts while the setup progress streams to the frontend. Your app doesn't need traditional loading states because this MCP Server feeds connection payloads directly into your active edge function execution context. When clients need to modify their setup, your agent invokes `update_connection` to patch the metadata values. The interface displays these configuration changes block-by-block as the Vercel AI SDK processes the incoming stream.

Real-time SCIM Directory Monitoring

The `create_directory` tool provisions a new Directory Sync endpoint for automated user management. Your application requests directory details and watches the tenant's user database synchronize without polling a separate backend API. Running `get_directory_users` pulls the active member roster directly into your streaming UI. Your users watch their team directory populate in real-time as the background sync matches their enterprise identity provider.

Instant Connection Diagnostics

The `health_check` tool monitors your connection to the BoxyHQ engine to prevent authentication downtime. Your agent runs this test before initiating any high-privilege configuration changes to verify the target endpoint responds. If a connection fails, the agent calls `get_connections` to compare active configurations against the target tenant ID. This diagnostic loop runs entirely within your edge-compatible runtime to resolve setup issues before they block user logins.

Setup guide

Set up BoxyHQ (Enterprise SSO) 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 BoxyHQ (Enterprise SSO) 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 BoxyHQ (Enterprise SSO) 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 BoxyHQ. 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 BoxyHQ (Enterprise SSO) 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 BoxyHQ (Enterprise SSO) MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and initialize the client using the Vinkius HTTP endpoint. Pass the tools directly into `streamText` and let your agent call `add_connection` or `get_connections` as needed. Keep in mind you must call `mcpClient.close()` once the generation finishes to prevent hanging connections.

Yes, because tool outputs stream directly to your frontend code. When the agent calls `get_connections` and finds a misconfigured SAML certificate, the Vercel AI SDK UI components render the error state immediately without waiting for a full page reload.

Absolutely. The Vinkius endpoint runs on a lightweight V8 sandbox, making it compatible with edge-deployed Next.js apps. Your edge functions route calls to `create_directory` or `delete_connection` without heavy Node.js dependencies.

Your agent uses `get_directory_groups` to fetch the group structure from the identity provider. It then parses the JSON payload to map enterprise groups to your local application roles on the fly.

Vinkius operates a zero-trust sandbox that handles your BoxyHQ API keys securely. It only passes raw SAML metadata and SCIM payloads like those from `get_directory_users` through ephemeral memory, meaning no user passwords or sensitive directory tokens are ever stored on Vinkius disks.

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