How to Use the Grid MCP in Vercel AI SDK

Stream your spreadsheet data directly into React components with Grid and 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 Grid MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time dashboard rendering for AI-SDK

Stop waiting for loading spinners. Use `list_grid_dashboards` and `list_worksheet_records` to push data straight into your UI components. Your AI client populates the frontend as the data streams in. It makes your application feel immediate and responsive to user input.

Manage operational data in AI-SDK

Your code controls the data state using `create_new_operational_record` and `update_worksheet_record` without leaving the framework. This MCP server gives your frontends direct write access to your spreadsheets. You maintain total control over how records are modified and saved.

Validate connectivity for AI-SDK

Avoid runtime errors by calling `check_api_health` before your app initiates a data fetch. This ensures your connection to the MCP server is live. You can build logic that alerts the user if the backend is unreachable.

Setup guide

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

Install the package and initialize the client with your endpoint. You will pass the tools directly into the streamText function to start executing operations.

Yes. Every request is authenticated and confined to the sandbox. Your private spreadsheet data never touches unauthorized memory spaces.

The server supports pagination through the record listing tools. You should fetch data in chunks to keep your UI performance high.

It does. Use the authProvider configuration in your setup to handle secure token exchange.

We enforce strict access control at the API layer. Only users with valid profiles can trigger sensitive operations like record deletion.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.