How to Use the Clustdoc MCP in Vercel AI SDK

Q: How do I trigger a Clustdoc invite using Vercel AI SDK?

Call sendonboardinginvitation inside your tool definition block. The SDK handles the response and lets your agent confirm to the user that the invitation email is on its way.

Q: Can Vercel AI SDK stream Clustdoc dossier list updates?

Yes. You can stream the output of listclientdossiers directly to your React components. The UI updates in real-time as the AI agent fetches the active onboarding pipelines.

Stream Clustdoc onboarding workflows and live dossier progress directly into your React app with the Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Clustdoc MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live dossier monitoring in your React UI

The `list_client_dossiers` tool lets your Vercel AI SDK application pull active client applications directly into your user-facing dashboard. Your frontend displays real-time updates as clients submit their documents, avoiding annoying page refreshes. By feeding `get_application_status_details` directly into streamText, your users watch their document checklist update live. This eliminates loading spinners and keeps clients informed about which files are still missing from their dossier.

Instant onboarding launch via Edge Functions

Starting a fresh client application is easy with the `launch_new_onboarding` tool. Your Vercel AI SDK setup triggers this action the moment a user signs up on your site. Once the application starts, the `send_onboarding_invitation` tool fires off the portal link. Clients get their invite instantly while the agent confirms the dispatch on the screen.

Dynamic template rendering with this MCP Server

Your Vercel AI SDK setup uses this MCP Server to fetch active workflow configurations with the `list_onboarding_templates` tool. Dynamic rendering lets users choose the correct checklist without lag. Using `get_workflow_configuration`, the AI inspects the specific requirements of the selected template. It then builds a custom preview in your Next.js app before the user commits to sending it.

Setup guide

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

Call `send_onboarding_invitation` inside your tool definition block. The SDK handles the response and lets your agent confirm to the user that the invitation email is on its way.

Yes. You can stream the output of `list_client_dossiers` directly to your React components. The UI updates in real-time as the AI agent fetches the active onboarding pipelines.

Pass your Vinkius token into the MCP client configuration. You can also use the SDK's authProvider if you need to manage individual user tokens for your team.

Yes. The Vinkius MCP Server runs in a sandboxed V8 environment, making it lightweight and fully compatible with Vercel's edge runtime.

All dossier data and file checklists are transmitted through Vinkius's zero-trust sandboxed tunnels. Your client's personal identification documents and application statuses never persist on our servers.

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