How to Use the FlowUs MCP in Vercel AI SDK

Q: How do I stream FlowUs database rows using the Vercel AI SDK?

You pass the tools from mcpClient.tools() into streamText. When the agent calls querydatabase, the SDK handles the tool call and streams the resulting rows directly back to your React frontend. Just make sure to call mcpClient.close() once the stream completes.

Q: How does the Vercel AI SDK handle authentication for FlowUs?

You configure the authProvider in the MCP client setup to manage OAuth tokens. This lets your agent run createdatabaserow securely on behalf of the logged-in user.

Q: What is the best way to handle errors during page updates?

Wrap your updatepage calls in standard SDK tool execution blocks. If a block update fails, the SDK catches the error and lets your agent retry or report the issue back to the user interface.

Pipe live FlowUs wiki updates and database queries straight to your Vercel AI SDK frontend with zero latency.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FlowUs MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Render FlowUs Database Queries Live in Vercel AI SDK

You don't want your users staring at a blank screen while your app fetches data. By pairing the Vercel AI SDK with this MCP Server, your agent queries live tables using `query_database` and streams the rows directly into React components. The data renders block-by-block as it arrives. Your frontend stays fast because the tool execution happens on the edge. The agent inspects the table structure using `get_database`, extracts the target records, and updates your UI state before the LLM even finishes generating its text response.

Instant Page Creation and Editing via Edge Functions

Building a collaborative editor means you need real-time page updates. This integration lets your Vercel AI SDK setup call `create_page` and `update_page` on the fly, feeding the raw markdown or block structure directly back into your UI. Instead of waiting for a heavy backend server to process the request, the edge-compatible client processes the block structure via `list_blocks` and pushes the modifications instantly. Your users watch their workspace evolve in real-time.

Direct Workspace User Syncing for Next.js Apps

Keep your application's user directory perfectly aligned with your workspace permissions. The agent calls `list_users` to pull active team members and maps them directly to your local React state. This setup avoids complex backend sync scripts. You fetch the fresh roster dynamically during the Next.js session using the Vercel AI SDK, giving your team immediate access to current collaborator details without manual imports.

Setup guide

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

You pass the tools from `mcpClient.tools()` into `streamText`. When the agent calls `query_database`, the SDK handles the tool call and streams the resulting rows directly back to your React frontend. Just make sure to call `mcpClient.close()` once the stream completes.

Yes, this server runs perfectly in edge environments. The integration uses lightweight HTTP transports, allowing your edge routes to run `get_page` and `list_pages` without cold-start delays.

You configure the `authProvider` in the MCP client setup to manage OAuth tokens. This lets your agent run `create_database_row` securely on behalf of the logged-in user.

Wrap your `update_page` calls in standard SDK tool execution blocks. If a block update fails, the SDK catches the error and lets your agent retry or report the issue back to the user interface.

Yes, your wiki pages, blocks, and database schemas are protected because this MCP Server runs within Vinkius's secure sandbox. The Vercel AI SDK only receives the specific JSON payloads returned by `list_blocks` or `get_database`, meaning raw API keys are never exposed to the browser.

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