How to Use the Retable MCP in Vercel AI SDK

Stream Retable data directly into your frontend with the Vercel AI SDK. Build real-time interfaces that respond as data arrives.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Retable MCP to Vercel AI SDK

Create your Vinkius account to connect Retable to Vercel AI SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Retable with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Real-time Retable data streaming

Feed your UI live updates by hooking Retable directly into your generation loop. You won't see any loading spinners because the data flows as the model processes it. Use `list_records` or `get_record` to push specific rows into your view components. Your users see the information populate instantly as it comes from the API.

Direct record manipulation

Update your database state without leaving your frontend logic. Your AI client can trigger `create_record` or `update_record` based on user input during a conversation. This keeps your application state in sync with the source of truth. You define the tool execution flow, and the SDK handles the transport between your UI and the MCP Server.

Schema navigation for your AI

Let your agent explore the database structure before it acts. It can call `list_tables` and `get_table` to understand the columns and relationships available in your project. This prevents errors caused by mismatched field names. Your model knows exactly what it's working with before it tries to write new entries.

Setup guide

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

Install the MCP client package and configure your transport. Once the endpoint is set, you pass the tools to your streamText function to start executing operations.

Yes, it manages incoming requests sequentially. You should implement your own optimistic UI updates if you need to mask latency during high-frequency writes.

Your data is only accessed through the authorized endpoint you provide. The MCP Server acts as a gatekeeper, ensuring your model only performs the actions you explicitly allow.

The tool will return an error object that you can catch in your code. You should handle this in your UI to alert the user that the action didn't complete.

The MCP protocol transmits tool results back to the client as they finish. While the database operation itself is atomic, the result is available as soon as the API responds.

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