How to Use the Lusha MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK agent verify Lusha data before saving it?

Yes. You can chain the agent's logic to run testlushaauth first, then pass the output of getpersonbyemail through your own validation layer before committing it to your database.

Plug Lusha data into your OpenAI Agents SDK workflow to turn cold lists into verified contact records instantly.

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 OpenAI Agents SDK

Create your Vinkius account to connect Lusha to OpenAI Agents 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated contact enrichment for OpenAI Agents SDK

Stop guessing if your lead data is fresh. Your agent can run `bulk_enrich_persons` to pull verified direct dials and emails directly into your context window. This MCP Server handles the handshake with your agent automatically. Once initialized, the agent uses `enrich_person_info` to fill gaps in your CRM records without manual intervention.

Real-time prospecting from within OpenAI Agents SDK

Use `prospect_new_leads` to find new targets based on your specific ICP criteria. Your agent identifies prospects and validates them against live B2B databases. Everything stays within your agent's execution loop. If you need to verify a specific company profile, the agent invokes `enrich_company_info` to grab firmographics before making a move.

Precise usage monitoring for OpenAI Agents SDK

Keep an eye on your credit consumption during high-volume scraping tasks. The agent checks `get_credit_balance` before starting any large batch job. If you hit a wall, `get_usage_stats` provides the data needed to adjust your scraping strategy. It keeps your production agent within budget without stopping the entire pipeline.

Setup guide

Set up Lusha MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Lusha tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Lusha tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Lusha tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Lusha Agent",
            instructions="You have access to Lusha tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

You instantiate the server via MCPServerStreamableHttp and pass it to your agent constructor. The SDK discovers the tools automatically, so you don't have to map them manually.

Yes. You can chain the agent's logic to run `test_lusha_auth` first, then pass the output of `get_person_by_email` through your own validation layer before committing it to your database.

Absolutely. Since the agent treats every tool call as an action, the SDK's guardrails inspect the Lusha output before the agent proceeds to the next step.

The agent receives a null or empty response. You should write a simple conditional check in your agent's prompt to handle these cases gracefully.

Yes. The connection is ephemeral and handled by the Vinkius sandbox. No data persists on our servers once your agent's session ends.

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