How to Use the NavAPI MCP in Vercel AI SDK

Q: How do I connect the NavAPI server to my Vercel AI SDK project?

You'll use the createMCPClient from @ai-sdk/mcp. Just pass the Vinkius endpoint URL into the transport options. Then you can get the tools and pass them to generateText or streamText.

Q: Can I filter the port list from NavAPI when using the Vercel AI SDK?

Yes, the getnauticalports tool accepts an optional country code. Your agent can pass that parameter to narrow down the list of maritime ports returned by the API.

Q: What's the best way to handle NavAPI streaming data with the Vercel AI SDK?

Use the streamText or streamObject function. The NavAPI tools are designed to work with the AI SDK's streaming capabilities, so you can pipe tool results directly into your UI for a live-updating display.

Stream maritime data directly into your UI. This NavAPI integration for the Vercel AI SDK lets you build live, responsive frontends.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NavAPI MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Plot Routes on Live Maps

This server gives you the tools to build an interactive route planner. Use `search_maritime_routes` to find a path between two points and `get_port_distance` to calculate the exact nautical miles. Your agent gets the data, and you can render it on a map in real time. Because you're using the Vercel AI SDK, the route data streams directly into your components. The user sees the path being drawn as your agent works, not after some loading spinner finishes. It's a much better experience than just waiting for a static result.

Monitor Real-Time Port Traffic

Give your users a live look into global port activity. The `get_port_vessel_traffic` tool provides current vessel counts and stats for any major port. You can feed this data straight into a dashboard or a table. When the data updates, your UI can update with it. Hook the streaming response into a React or Svelte component to show ships entering and leaving a harbor. It's the ideal way to build a user-facing maritime intelligence app.

Build UIs with this MCP Server

This MCP server isn't just for background tasks. It's built for creating frontends. The tools `get_nautical_ports` and `list_nautical_charts` let you create dynamic dropdowns and lists that populate on the fly. A user could select a country, and your app immediately shows all available ports. Or they could define a geographic area, and your UI instantly lists the relevant nautical charts. This is how you build fast, interactive tools for dispatchers and analysts.

Setup guide

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

You'll use the `createMCPClient` from `@ai-sdk/mcp`. Just pass the Vinkius endpoint URL into the transport options. Then you can get the tools and pass them to `generateText` or `streamText`.

Yes, the `get_nautical_ports` tool accepts an optional country code. Your agent can pass that parameter to narrow down the list of maritime ports returned by the API.

Use the `streamText` or `streamObject` function. The NavAPI tools are designed to work with the AI SDK's streaming capabilities, so you can pipe tool results directly into your UI for a live-updating display.

No, Vinkius handles it. Your single Vinkius endpoint token is all you need. The `createMCPClient` function can take an auth provider, but for this managed server, the URL already includes your token.

Your queries for port names, vessel traffic, and route coordinates are processed in an ephemeral sandbox. The data streams from the MCP server through your Edge Function directly to the user's browser. Vinkius does not store the results of your maritime queries.

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