How to Use the Xata MCP in Vercel AI SDK

Q: How do I use Xata with Vercel AI SDK for SQL?

You call executesql through your agent. The results stream back to your client in real-time, so the user sees the data appear instantly rather than waiting on a single loading screen.

Q: What kind of data does Xata provide via Vercel AI SDK?

You can get detailed organizational info using getorganization, plus project limits with getprojectlimits. All this metadata is available for your agent to process and display.

Q: Can I manage users and keys using Xata and Vercel AI SDK?

Yes. You can list user-scoped API keys with listuserapikeys or even bulk delete them via deleteuserapikeys. This lets your agent handle key rotation for security.

Show Xata database operations happening live in your UI with 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 Xata MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time Database Querying

You execute single or batch SQL queries using `execute_sql`. This tool handles the raw interaction, streaming data results directly to your user interface. You see query outputs appear live, eliminating loading spinners. This is perfect for building product dashboards where end users need immediate feedback on database requests, powered by Xata.

Managing Organizational Setup

Need to set up a new environment? Start by calling `create_organization` to spin up an entire Xata org. Later, you can use `list_projects` and `create_project` to scaffold out the necessary workspace structure. Your agent handles all these steps, allowing your client application to manage the lifecycle of multiple projects within the Vercel AI SDK.

Checking Branch Health Metrics

Don't guess how healthy a branch is. Use `get_branch_metrics` to pull observability data—things like CPU, memory, and disk usage—for any given branch. The results stream back instantly. This lets your client build real-time monitoring dashboards that display performance metrics straight from the MCP Server.

Setup guide

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

You call `execute_sql` through your agent. The results stream back to your client in real-time, so the user sees the data appear instantly rather than waiting on a single loading screen.

You can get detailed organizational info using `get_organization`, plus project limits with `get_project_limits`. All this metadata is available for your agent to process and display.

Yes. You can list user-scoped API keys with `list_user_api_keys` or even bulk delete them via `delete_user_api_keys`. This lets your agent handle key rotation for security.

The MCP Server handles the underlying authorization. When you call a tool like `create_branch`, your client is authenticated via an endpoint token, keeping the connection secure and reliable.

You manage organizational structure, projects, branches, and associated API keys. The agent provides methods to list organizations (`list_organizations`) and members.

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