How to Use the ToolJet MCP in Vercel AI SDK

Q: What is the best way to query data using ToolJet with Vercel AI SDK?

Use querytable when you know exactly what columns and tables you need. The streaming nature of the Vercel AI SDK makes this ideal because the user sees the results appear live, which is a huge UX win.

Q: Can I run multi-step processes like logging data using ToolJet with Vercel AI SDK?

Yes. You can chain tools together: first querytable to get an ID, then use that ID in the payload for insertrow. The result streams back through your UI after every step.

Q: Does ToolJet handle database schema discovery with Vercel AI SDK?

The listtables tool lets your agent check which tables are available before running a query. This saves time because the agent can verify the structure first, preventing runtime errors in your client code.

Q: Is ToolJet reliable for triggering background processes with Vercel AI SDK?

Absolutely. The triggerworkflow tool sends a standard webhook call to start the process. Since this is handled on the server side, your frontend remains responsive while the backend work happens.

Display ToolJet data live in your UI using Vercel AI SDK streaming responses.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ToolJet MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query and display structured database records.

The `query_table` tool lets your agent fetch specific data from a ToolJet Database table. You stream the resulting rows directly into React or Next.js components, so users see the data pop up instantly—no loading spinner required. The AI SDK handles the result streaming perfectly. This means complex database lookups feel real-time to the end user because they see the data appearing as it's retrieved by the agent.

Update databases with single actions.

Need to log something? The `insert_row` tool allows your agent to add new records directly into a ToolJet Database table. You write code that calls this function, and the data writes itself automatically. The result streams back immediately, confirming the record creation to your client-side code. It’s fast, reliable database interaction designed for user-facing applications.

Automate backend processes with workflows.

The `trigger_workflow` tool lets your agent initiate any ToolJet Workflow via a simple webhook call. You pass necessary parameters (like an ID or status) to kick off complex business logic. Your application calls this, and the workflow runs on the backend while your frontend keeps updating. It’s perfect for running background tasks that need to update visible state.

Setup guide

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

This server touches database records (the data type). Always ensure your credentials and environment variables are secured within the Edge Function. The streaming nature of the SDK helps minimize exposure by handling results in small, manageable chunks.

Use `query_table` when you know exactly what columns and tables you need. The streaming nature of the Vercel AI SDK makes this ideal because the user sees the results appear live, which is a huge UX win.

Yes. You can chain tools together: first `query_table` to get an ID, then use that ID in the payload for `insert_row`. The result streams back through your UI after every step.

The `list_tables` tool lets your agent check which tables are available before running a query. This saves time because the agent can verify the structure first, preventing runtime errors in your client code.

Absolutely. The `trigger_workflow` tool sends a standard webhook call to start the process. Since this is handled on the server side, your frontend remains responsive while the backend work happens.

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