How to Use the Mashvisor MCP in Vercel AI SDK

Q: How do I connect Mashvisor to my Vercel AI SDK project?

Install the @ai-sdk/mcp package and define your transport layer. Use createMCPClient with the Vinkius endpoint URL. Pass the returned tools into your streamText function to start fetching real estate data from the Mashvisor MCP server.

Q: Can Vercel AI SDK stream Mashvisor property data directly to React components?

Yes. When the agent calls searchproperties, the Vercel AI SDK streams the resulting investment metrics straight to your UI. Users see the property filters and ROI calculations render in real-time.

Stream Mashvisor real estate metrics straight into your React app 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 Mashvisor MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Live Dashboards with Vercel AI SDK

The `get_investment_analysis` tool feeds raw capitalization rates and cash-on-cash return figures straight to your Vercel AI SDK implementation. Your users watch as the AI streams ROI comparisons between short-term and traditional rentals directly into your Next.js components. No loading spinners delay the output. You call `mcpClient.tools()` to grab the endpoints and pass them to your stream handler. When a user asks about a specific address, the agent hits `get_property` and renders the building attributes instantly on the edge.

Render Neighborhood Data Instantly

The `list_neighborhoods` tool grabs aggregate investment data across target zip codes for immediate UI consumption. As the AI processes the request, your Svelte or Vue frontend updates with live metrics on local market viability. You give your end users instant access to neighborhood-level real estate intelligence. Combining this with `get_city_listings` lets your application filter active properties by days on market and price history. The Vercel framework handles the transport layer while the Mashvisor MCP server pushes the exact market status your users requested.

Compare Rental Strategies on the Fly

The `get_rental_rates` tool pulls traditional rent distribution statistics so your application can evaluate long-term investment potential. Your prompt triggers the agent to fetch these numbers alongside short-term metrics from `get_airbnb_listings`. The user sees the side-by-side financial breakdown appear character by character. To check seasonal dips, the agent invokes `get_historical_performance`. You just ensure `mcpClient.close()` runs when the stream finishes. The entire real estate analysis happens natively within your frontend architecture via the MCP client.

Setup guide

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

Install the `@ai-sdk/mcp` package and define your transport layer. Use `createMCPClient` with the Vinkius endpoint URL. Pass the returned tools into your `streamText` function to start fetching real estate data from the Mashvisor MCP server.

Yes. When the agent calls `search_properties`, the Vercel AI SDK streams the resulting investment metrics straight to your UI. Users see the property filters and ROI calculations render in real-time.

The Vinkius HTTP transport handles edge environments natively. Your Next.js app can request `get_airbnb_property` data without spinning up a heavy Node backend. Just remember to close the connection after the stream completes.

Vinkius manages the authentication layer entirely. You provide your single endpoint token in the HTTP transport configuration. The server handles the underlying API credentials automatically.

Your search parameters and target city inputs process within a V8 Isolate Sandbox. Vinkius destroys the execution environment the moment the `list_properties` tool returns its data. Zero residual data remains on the system.

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