How to Use the Mapillary MCP in Vercel AI SDK

Q: How do I search for Mapillary imagery using Vercel AI SDK?

You initiate a search by calling searchimages with your bounding box coordinates. The MCP Server returns a list of image IDs which you then pass to your UI layer.

Q: Can Vercel AI SDK display traffic signs from Mapillary?

Yes. You fetch sign data using getmapfeatures and then parse the detection confidence. The AI client handles the logic to display these on your map interface.

Q: What is the coordinate format for this MCP server?

Use the standard minlon,minlat,maxlon,maxlat format. This works across all search tools in the server.

Stream Mapillary street-level imagery and spatial data directly into your Vercel AI SDK frontends for real-time visual feedback.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mapillary MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search and retrieve imagery with Vercel AI SDK

You can pull street-level photos into your app UI by using `search_images` to define a geographic bounding box. The results flow straight to your frontend components without extra middleware. Use `get_image` to grab specific metadata like capture dates and high-res thumbnail URLs. Your users get a live view of the street as the AI processes the location data.

Extract infrastructure data for Vercel AI SDK

Identify traffic signs and road features by triggering `get_map_features` within your agent stream. This tool returns precise GPS coordinates for every detected object in the area. Once you have a feature ID, call `get_detection_value` to pull the specific metadata. You'll see the exact sign type and confidence score populated on your dashboard immediately.

Analyze sequences with Vercel AI SDK

Map large areas by querying `search_sequences` to list all available image paths within a specific coordinate range. This provides the context your AI client needs to map out a full route. After getting a sequence ID, use `get_sequence` to fetch the full list of associated images. It's the fastest way to build a coherent visual history of a road segment.

Setup guide

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

You initiate a search by calling `search_images` with your bounding box coordinates. The MCP Server returns a list of image IDs which you then pass to your UI layer.

Yes. You fetch sign data using `get_map_features` and then parse the detection confidence. The AI client handles the logic to display these on your map interface.

It does. Because the tools connect via HTTP, your Vercel AI SDK application can stream the tool outputs as they arrive from the API.

Use the standard min_lon,min_lat,max_lon,max_lat format. This works across all search tools in the server.

The server transmits only the specific detection metadata and image URLs you request. No personal user data or private credentials reside on our infrastructure.

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