How to Use the Foursquare MCP in Vercel AI SDK

Q: How does Vercel AI SDK stream photos using the Foursquare MCP Server?

The agent calls getplacephotos to retrieve the media URLs. Since the SDK supports tool call streaming, the image cards render in the UI the moment the server returns the URLs.

Get real-time Foursquare location data streaming directly into your Vercel AI SDK frontend using our MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Foursquare MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live Foursquare data with Vercel AI SDK

Stop making users wait for heavy API payloads to resolve. This integration feeds live venue details straight into your UI components. Your agent calls `search_places` or `autocomplete_venues` and the results render instantly on the screen as they arrive. It runs on Edge Functions without cold starts. By wrapping the MCP Server connection in your serverless endpoints, you can pipe photos from `get_place_photos` directly to the client without setting up a dedicated backend.

Exact location matching and verification

When users type messy addresses, your agent cleans them up instantly. The `match_venue_exactly` tool checks your input against Foursquare's master database to ensure you do not store duplicate records. Once you have a clean match, you can pull rich metadata. Use `get_place_details` to extract structural properties like operating hours and contact info, then display them in your React or Next.js components.

Spatial search within custom boundaries

Drawing on a map is useless if your backend cannot parse the coordinates. This toolset lets your agent run complex queries like `search_within_polygon` based on custom UI selections. If a user wants to find coffee shops within a walking zone, the agent handles the math. It queries `search_within_radius` to filter out irrelevant spots and only returns what actually fits the boundary.

Setup guide

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

Cache your responses at the Edge. You can store the results of `get_place_details` or `list_venue_categories` in a fast KV store to avoid hitting Foursquare limits on every user interaction.

Yes, the MCP client setup is lightweight and works fine in Edge environments. You just need to initialize the HTTP transport and pass the tools to streamText or generateText.

The agent calls `get_place_photos` to retrieve the media URLs. Since the SDK supports tool call streaming, the image cards render in the UI the moment the server returns the URLs.

No. Vinkius hosts the MCP Server for you, so you only need to call the HTTP endpoint from your Next.js API routes or server actions.

The server only processes the coordinate pairs and search queries you send to tools like `search_nearby_venues`. Vinkius runs this in a zero-trust sandbox, so no persistent history or user coordinates are stored on the host after the request finishes.

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