How to Use the Lusha MCP in Vercel AI SDK

Q: Can I stream bulk contact data using Vercel AI SDK and Lusha?

Yes, you can stream bulk results by passing the bulkenrichpersons tool directly to streamText. The AI client yields the enriched phone numbers and emails as they arrive, rendering them instantly in your React or Next.js frontend.

Q: How do I monitor my Lusha credit usage inside a Vercel AI SDK application?

You can have your agent call getcreditbalance or getusagestats directly within your streaming loop. This lets your frontend display real-time API usage metrics to users without requiring a separate backend dashboard.

Q: What happens if a contact search returns no results?

The getpersonbyemail tool returns an empty payload which your AI client handles gracefully. You can configure your streaming UI to show a friendly fallback message instead of breaking the chat render.

Q: How does this setup secure sensitive B2B contact details?

All business emails and direct dials fetched via enrichpersoninfo are processed within Vinkius's zero-trust MCP sandbox. Your credentials are never exposed to the client-side frontend, keeping the underlying API calls completely hidden from the browser.

Feed live B2B contact data directly into your Next.js frontend with Vercel AI SDK and Lusha without making users wait.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lusha MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live B2B profile lookups using the Lusha MCP Server

Your Next.js users don't want to stare at a blank screen while your app fetches direct dials. By hooking the Lusha MCP Server into `streamText`, you can pipe verified lead details straight to the UI as they resolve. The AI client uses `enrich_person_info` to grab direct phone numbers and drops them right into your React components without lag. This MCP setup completely bypasses the typical loading spinner headache. If a user drops a corporate email into your chat interface, the SDK triggers `get_person_by_email` and renders the workspace profile live. It feels fast because the data flows chunk by chunk.

Bulk enrich lead lists on the edge

Running heavy data operations in Edge Functions requires a lightweight footprint and fast execution. When your application processes a batch of raw leads, your AI agent calls `bulk_enrich_persons` to clean up the names, titles, and phone numbers. The Vercel AI SDK handles these asynchronous tool calls without hitting cold start bottlenecks. You can also run quick safety checks on your operational limits before launching large runs. Have your agent trigger `get_credit_balance` to check your API wallet. This keeps your edge routes from throwing errors or burning through your budget mid-stream.

Real-time company firmographics

Building dynamic B2B dashboards requires pulling company data on the fly. When a user enters a domain, the SDK invokes `enrich_company_info` to fetch employee count, industry, and revenue data. The AI client then structures this raw data into clean UI elements instantly. If you need to expand a list of target accounts, `prospect_new_companies` lets your agent search for matching businesses based on specific criteria. The results stream back to the UI, allowing users to watch their prospect list build itself in real-time.

Setup guide

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

You pass your credentials securely using the authProvider configuration when initializing the client. The SDK manages the transport layer, letting your AI client run `test_lusha_auth` behind the scenes to verify your connection before executing any contact queries.

Yes, you can stream bulk results by passing the `bulk_enrich_persons` tool directly to streamText. The AI client yields the enriched phone numbers and emails as they arrive, rendering them instantly in your React or Next.js frontend.

You can have your agent call `get_credit_balance` or `get_usage_stats` directly within your streaming loop. This lets your frontend display real-time API usage metrics to users without requiring a separate backend dashboard.

The `get_person_by_email` tool returns an empty payload which your AI client handles gracefully. You can configure your streaming UI to show a friendly fallback message instead of breaking the chat render.

All business emails and direct dials fetched via `enrich_person_info` are processed within Vinkius's zero-trust MCP sandbox. Your credentials are never exposed to the client-side frontend, keeping the underlying API calls completely hidden from the browser.

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