How to Use the Datalastic Maritime MCP in Vercel AI SDK

Feed real-time AIS vessel locations and port details straight to your React UI using 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 Datalastic Maritime MCP to Vercel AI SDK

Create your Vinkius account to connect Datalastic Maritime 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 Datalastic Maritime with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Render Live Vessel Positions in Your Vercel AI SDK UI

Your users don't want to wait for heavy API payloads to resolve before seeing where a cargo ship is. By pairing the Vercel AI SDK with this MCP Server, your LLM calls `get_vessel_status` and streams the coordinates directly to the frontend, allowing you to render SVG maps or map markers on the fly. If a user searches for a fleet, the agent calls `find_vessels_in_radius` to pull live coordinates. The map UI updates instantly as the vessel tracking chunks arrive, bypassing the typical loading spinner lag.

Instant Port Directories via Edge Functions

Digging through global port databases slows down maritime logistics dashboards. This MCP configuration uses `search_ports_by_name` and `search_ports_by_country` to fetch specific dock locations without spinning up heavy database instances. Because the SDK is edge-compatible, these port lookups run near your users. Running `get_port_details` inside an Edge Function keeps the latency low enough for cargo coordinators to query global docks in plain English.

Generate Interactive Vessel Spec Sheets on the Fly

When brokers need to check cargo capacities, they ask specific technical questions. The agent uses `get_vessel_pro_specs` to pull gross tonnage, draft depth, and build details, formatting them into clean UI components. Coupling this with `get_vessel_history` renders historical AIS tracks alongside the technical specs. Your React components receive this telemetry from the MCP endpoint piece by piece, painting a complete picture of the ship's journey.

Setup guide

Set up Datalastic Maritime 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 Datalastic Maritime 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 Datalastic Maritime 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 Datalastic. 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 Datalastic Maritime 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 Datalastic Maritime MCP in Vercel AI SDK

You map the tools returned by the MCP Server directly to your `streamText` function. When the agent triggers `get_vessel_status`, the coordinates flow as tool calls that your React hooks capture to update map markers instantly.

Yes, the Vinkius endpoint handles the heavy lifting, allowing your edge-deployed agent to call `find_vessels_in_radius` without exceeding runtime memory limits. This keeps your maritime dashboards fast and responsive.

You configure the Vinkius token once in your environment variables when initializing the client. The SDK sends this single token to authenticate all calls for tools like `get_vessel_pro_specs` and `get_vessel_history`.

You should instruct your agent to narrow down the query using `search_maritime_vessels` before fetching full histories. The MCP client streams the initial list so users can select the correct hull number before pulling deeper telemetry.

All vessel positions and port lookups route through an isolated V8 sandbox on Vinkius. Your API keys for maritime data are never exposed to the client browser, keeping your tracking queries private.

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