How to Use the Mapbox (Maps & Geospatial) MCP in Vercel AI SDK

Q: How do I install the Mapbox (Maps & Geospatial) MCP Server with Vercel AI SDK?

Run npm install ai @ai-sdk/mcp to get the core packages. Initialize the connection using createMCPClient with your HTTP endpoint, then pass the tools directly into your generateText or streamText calls.

Q: How does the Mapbox (Maps & Geospatial) MCP Server handle session-based geocoding in Vercel AI SDK?

Use geocodingsession to group consecutive keystrokes into a single session. This prevents your Vercel AI SDK app from spamming the API and keeps your Mapbox billing predictable during live typing.

Q: What is the best way to clean up Mapbox (Maps & Geospatial) MCP Server connections?

You must call mcpClient.close() at the end of your execution block. This prevents socket leaks and ensures your Next.js serverless functions spin down cleanly after streaming the spatial data.

Stream live route geometry and spatial data straight to your Next.js components using the 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 Mapbox (Maps & Geospatial) MCP to Vercel AI SDK

Create your Vinkius account to connect Mapbox (Maps & Geospatial) 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 Mapbox (Maps & Geospatial) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live route maps to your UI with Vercel AI SDK

The `generate_static_map` tool spits out map image URLs that your AI client can render instantly in the browser. Instead of waiting for a backend server to process, the Vercel AI SDK streams these visual assets directly into your React or Next.js components. You set up the client using `createMCPClient` and pass the tools directly to `streamText`. When your agent triggers a map generation, the UI updates in real-time, bypassing the typical lag of traditional API setups. Make sure to call `mcpClient.close()` once the streaming session completes.

Real-time geocoding sessions for instant UI feedback

The `geocoding_session` tool handles autocomplete operations directly within user-facing text inputs. As the user types, the Vercel AI SDK streams matching addresses onto the screen, keeping things fast during address entry. This setup runs efficiently on Edge Functions, keeping latency low. You get fast address resolution without spinning up hefty backend containers, and you can reverse the search instantly using `reverse_geocode` when users drop a pin on the map.

Dynamic delivery route calculation in Next.js

The `get_directions` tool calculates transit paths between multiple points instantly. Your AI client calls this tool to update the user's route on the fly, showing walking, driving, or cycling paths directly in the chat interface using this MCP Server. Combining this with `get_distance_matrix` lets your agent present multiple travel options to the user. The Vercel AI SDK handles the data transfer, allowing you to display estimated travel times before the final route coordinates finish loading.

Setup guide

Set up Mapbox (Maps & Geospatial) 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 Mapbox (Maps & Geospatial) 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 Mapbox (Maps & Geospatial) 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 Mapbox. 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 Mapbox (Maps & Geospatial) 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 Mapbox (Maps & Geospatial) MCP in Vercel AI SDK

Run `npm install ai @ai-sdk/mcp` to get the core packages. Initialize the connection using `createMCPClient` with your HTTP endpoint, then pass the tools directly into your `generateText` or `streamText` calls.

Yes, this MCP Server is compatible with Edge runtimes. Because the Vercel AI SDK relies on lightweight HTTP transports, you can fetch route data using `get_directions` without hitting cold-start delays.

Use `geocoding_session` to group consecutive keystrokes into a single session. This prevents your Vercel AI SDK app from spamming the API and keeps your Mapbox billing predictable during live typing.

You must call `mcpClient.close()` at the end of your execution block. This prevents socket leaks and ensures your Next.js serverless functions spin down cleanly after streaming the spatial data.

Your coordinate pairs and address queries remain entirely in your private V8 sandbox. Vinkius does not store the route geometry or location strings processed by `get_directions` or `search_places`, passing them directly to Mapbox via secure HTTPS.

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