How to Use the Wolai MCP in Vercel AI SDK

Q: How do I check the available schema for Wolai using Vercel AI SDK?

You call getdatabase to get the current database schema. Because you're using the Vercel AI SDK, this entire process streams its output, showing the developer exactly when and how that schema data is returned.

Q: What happens if I need a list of all Wolai pages for my application with Vercel AI SDK?

You use listpages to fetch the index of existing content. This function provides a simple array of page titles and IDs that your agent can then feed into other UI components.

Q: Can I query Wolai databases and stream results with Vercel AI SDK?

Yep. Running querydatabase pulls structured data, and the Vercel AI SDK ensures those rows appear in your frontend component as they are processed. You don't wait for a big chunk of data; it streams live.

Q: Does the MCP Server support listing users when using Vercel AI SDK?

Absolutely. The listusers tool pulls all workspace user accounts, letting your agent build out an accurate list for a user directory component in your application.

Get real-time Wolai information into your UI using 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 Wolai MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Displaying Wolai data live with Vercel AI SDK

When you call `get_database`, your agent retrieves the schema and row data, streaming it directly to the user interface. Users see records appear in real-time as the MCP Server responds, eliminating the loading spinner delay. You can also use `list_pages` to show a live list of available Wolai pages. This means the client knows exactly which content exists without requiring an extra API call after initial page load.

Managing Wolai Content via Vercel AI SDK

Need to create new structured data? Use `create_database_row` to insert a record into the database, and your agent streams confirmation back to the user. This makes the creation process feel immediate and integrated into the frontend experience. Developers can use `get_workspace_info` to pull organizational details and stream that metadata directly into an admin panel's UI elements.

Real-time Wolai Page Construction with Vercel AI SDK

`list_blocks` lets your agent read the content structure within a specific page. This is key for building rich UIs that need to display exactly what blocks are present. If you combine this with `get_page`, you can stream both the overall details and the block list simultaneously, giving the user instant visibility into the Wolai document structure.

Setup guide

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

You call `get_database` to get the current database schema. Because you're using the Vercel AI SDK, this entire process streams its output, showing the developer exactly when and how that schema data is returned.

You use `list_pages` to fetch the index of existing content. This function provides a simple array of page titles and IDs that your agent can then feed into other UI components.

Yep. Running `query_database` pulls structured data, and the Vercel AI SDK ensures those rows appear in your frontend component as they are processed. You don't wait for a big chunk of data; it streams live.

Absolutely. The `list_users` tool pulls all workspace user accounts, letting your agent build out an accurate list for a user directory component in your application.

The server handles organizational metadata and structured content. Specifically, it manages `database rows`, which contain the actual business data points you're tracking in Wolai.

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