How to Use the Lusha MCP in Mastra AI

Q: How do I verify my Lusha MCP connection within a Mastra AI agent?

You can call testlushaauth or getaccountinfo during agent initialization. This ensures your API keys are valid and the server is responsive before starting any automated workflows.

Q: Can I use this setup to find new business leads autonomously?

Yes, your agent can run prospectnewleads to find contacts matching your ideal profile. It can then chain that data to enrich their contact details in a single automated run.

Run reliable, multi-step B2B enrichment workflows with Mastra AI and the Lusha 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 Lusha MCP to Mastra AI

Create your Vinkius account to connect Lusha to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build automated B2B enrichment pipelines with Mastra AI

Mastra specializes in complex, multi-step agent workflows that can handle API failures gracefully. When a new contact enters your system, the framework triggers `enrich_person_info` to gather direct dials. If the initial lookup fails or hits a rate limit, Mastra's built-in retry engine automatically backs off and tries again without crashing your script. You can set up conditional branches based on the data returned. For instance, if `get_person_by_linkedin` returns a valid profile, the agent proceeds to update your CRM. If not, it routes the lead to a secondary queue or triggers `get_person_by_email` to find another angle.

Safe budget boundaries for autonomous agents

Running agents on autopilot can quickly drain your wallet if you don't set up guardrails. Before executing a large batch run, your Mastra workflow can call `get_credit_balance` to verify you have enough credits. If the balance falls below your threshold, the workflow pauses and alerts your team via Slack. This MCP integration prevents runaway loops from burning through your API limits. You can also monitor operational velocity by querying `get_usage_stats` at the start of every cron job, keeping your automated outbound pipelines entirely predictable and cost-effective.

Automated target account prospecting

Finding new accounts shouldn't require manual searching. Mastra agents can use `prospect_new_companies` to scan for businesses matching your target profile. Once the agent identifies a company, it immediately triggers `enrich_company_info` to pull down firmographics like employee count and industry. You can configure the framework to require human approval before running high-cost tools. This means your agent can queue up prospects but wait for a quick thumbs-up before calling `bulk_enrich_companies` to pull the trigger on data acquisition.

Setup guide

Set up Lusha MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Lusha tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "lusha-alternative-mcp-client",
  servers: {
    "lusha-alternative-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Lusha Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Lusha tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Lusha transactions"
);
console.log(result.text);

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 Mastra AI

Mastra AI uses built-in exponential backoff to handle rate limits or network hiccups automatically. If `enrich_person_info` encounters an error, the framework retries the call before failing the workflow.

Yes, you can set requireToolApproval on high-credit tools like `bulk_enrich_persons` or `bulk_enrich_companies`. This pauses the Mastra AI agent and waits for a manual confirmation before spending your credits.

You can call `test_lusha_auth` or `get_account_info` during agent initialization. This ensures your API keys are valid and the server is responsive before starting any automated workflows.

Yes, your agent can run `prospect_new_leads` to find contacts matching your ideal profile. It can then chain that data to enrich their contact details in a single automated run.

Your Lusha API credentials and the fetched B2B contact records are isolated within Vinkius's ephemeral MCP runtime environment. No raw contact data is stored on our servers, ensuring your pipeline complies with enterprise security standards.

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