How to Use the CARTO MCP in Vercel AI SDK

Q: What happens if a CARTO query takes too long in Vercel AI SDK?

Use createasyncsqljob instead of synchronous calls. This prevents timeouts and lets your UI poll for results in the background.

Stream real-time spatial analytics and routing directly into your React or Next.js frontends using CARTO and 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 CARTO MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live spatial data in your UI

Your React components react instantly as the AI processes spatial SQL queries. Using `execute_sql_query`, you pipe data straight from your warehouse into your app's state without waiting for slow backend roundtrips. This MCP Server pushes results through the stream so your users see maps update as the agent talks. It turns your interface into a live dashboard for geography-heavy insights.

Vercel AI SDK and CARTO routing

Calculate driving paths and reachability polygons on the fly for your end users. The `calculate_route` and `calculate_isoline` tools output GeoJSON that maps libraries consume immediately. Your code handles the geometry without extra parsing logic. You simply pass the tool output to your map layer and the route appears on the screen.

Bulk geocoding for user inputs

Process address lists from your users and turn them into coordinates while they wait. The `geocode_batch_addresses` tool handles large sets so your app doesn't hang while fetching location data. Everything stays within the stream. You keep the user engaged by showing progress as the agent cleans and maps the imported data.

Setup guide

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

You initialize the client via the Vercel MCP transport and pass the URL provided by Vinkius. Once initialized, your agents gain direct access to the full toolset.

Yes, it runs on the edge. You keep latency low by executing spatial logic near your users while the agent manages the connection.

Your data remains within your warehouse connection. The server only transmits the specific GeoJSON or SQL results required for your current prompt.

Use `create_async_sql_job` instead of synchronous calls. This prevents timeouts and lets your UI poll for results in the background.

We enforce strict transport security for all address strings sent to the LDS API. Your raw customer data is never stored in the MCP layer or the AI context.

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