How to Use the AgentFire MCP in Vercel AI SDK

Q: How do I connect the AgentFire MCP Server to Vercel AI SDK?

Install @ai-sdk/mcp and use createMCPClient with your HTTP transport URL. Pass the exposed tools directly to streamText or generateText.

Q: Can Vercel AI SDK stream AgentFire property data?

Yes. When the agent calls searchlistings, the SDK streams the raw JSON back to your frontend. You render the property details in React as they arrive.

Q: What happens if the AgentFire API goes down during a Vercel AI SDK chat?

The client throws an error in the stream. You should run checkagentfirestatus before initiating heavy queries to catch connection issues early.

Stream real estate leads and live property data directly into your React 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 AgentFire MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Property Listings to the UI

The `search_listings` tool pulls live property data straight from your AgentFire database into your Vercel AI SDK frontend. End users never stare at loading spinners while waiting for real estate details. The SDK streams the JSON response directly into your React components as the agent fetches it. You can also use `get_listing` to pull specific property specs when a buyer clicks a map pin. Combine this with `list_listings` to render an entire neighborhood's inventory on the fly. The data appears in the browser instantly.

Capture Leads in Real Time

The `create_lead` tool pushes new prospect data into your brokerage system without requiring a page reload. You just need an email address to instantiate the record. The Edge Function handles the routing while your frontend shows a success state immediately. If a user updates their preferences in your chat interface, the agent triggers `update_lead` to modify specific fields. You keep the CRM accurate without forcing buyers to fill out static forms.

AgentFire MCP Server Setup

The `check_agentfire_status` tool verifies your API connection before the user starts chatting. Connecting this MCP Server takes two lines of code with `createMCPClient`. You pass the HTTP transport URL, call `mcpClient.tools()`, and feed the result into `streamText`. The agent automatically knows how to read your brokerage data. Just remember to invoke `mcpClient.close()` when the session ends to prevent memory leaks in your Next.js application.

Setup guide

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

Install `@ai-sdk/mcp` and use `createMCPClient` with your HTTP transport URL. Pass the exposed tools directly to `streamText` or `generateText`.

Yes. When the agent calls `search_listings`, the SDK streams the raw JSON back to your frontend. You render the property details in React as they arrive.

The client throws an error in the stream. You should run `check_agentfire_status` before initiating heavy queries to catch connection issues early.

No. The agent extracts an email address from the chat context and executes `create_lead` automatically.

Vinkius runs the AgentFire MCP Server in an ephemeral V8 Isolate Sandbox. When your frontend requests a lead's email or phone number, the data passes through a zero-trust tunnel and terminates the moment the session closes.

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