How to Use the Lusha MCP in CrewAI

Q: Can a CrewAI agent check my Lusha credit balance before running a task?

Yes, you can assign a supervisor agent to run getcreditbalance before the rest of the crew starts prospecting. If the balance is too low, the agent can pause the workflow.

Q: How do CrewAI agents handle bulk data enrichment with Lusha?

Your agents can use bulkenrichcompanies or bulkenrichpersons to process lists of prospects. The framework handles the sequential execution, passing the enriched data between agents for final validation.

Q: What happens if the API key is invalid?

The crew will fail to initialize, but you can run testlushaauth to diagnose connection issues. This helper tool quickly verifies your API key status before your agents start their runs.

Deploy specialized multi-agent teams to source and enrich B2B leads autonomously using CrewAI and Lusha.

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 CrewAI

Create your Vinkius account to connect Lusha to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate multi-agent B2B research teams

CrewAI excels at running specialized agent teams that collaborate on complex tasks. You can assign one researcher agent to find target accounts using `prospect_new_companies`, while an analyst agent uses `enrich_company_info` to filter them by size and industry. This division of labor keeps your outbound pipeline running like an assembly line. Because the agents share memory, they pass context back and forth without losing track of the goal. Once the company profile is locked in, a third agent can trigger `prospect_new_leads` to identify decision-makers and fetch their direct contact details.

Autonomous lead enrichment and validation

Manually verifying contact lists is a waste of your sales team's time. With this MCP Server, your CrewAI agents can take raw lists and run `bulk_enrich_persons` to pull verified emails and phone numbers. The agents analyze the returned data to ensure accuracy before writing to your database. If an email looks questionable, the agent can double-check the profile using `get_person_by_linkedin`. This multi-step validation process ensures your sales team only reaches out to active, verified contacts, protecting your domain reputation.

Automated budget protection for your crew

Autonomous crews can run wild if they aren't supervised. You can designate a monitor agent whose sole job is to run `get_credit_balance` before any major prospecting run begins. If your API balance is running low, the agent can halt the crew's execution and notify your sales operations team. This setup keeps your operational costs completely transparent. By tracking `get_usage_stats` dynamically, your crew can adjust its search volume to match your monthly budget limits, preventing unexpected API bills.

Setup guide

Set up Lusha MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Lusha tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Lusha Analyst",
    goal="Access and analyze Lusha data via MCP.",
    backstory="Expert analyst with direct Lusha access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Lusha transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Lusha Analyst",
        goal="Access and analyze Lusha data via MCP.",
        backstory="Expert analyst with direct Lusha access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Lusha transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You register the Lusha MCP Server URL in your agent configuration using the mcps parameter. This exposes tools like `enrich_person_info` specifically to your researcher agent while keeping other agents lightweight.

Yes, you can assign a supervisor agent to run `get_credit_balance` before the rest of the crew starts prospecting. If the balance is too low, the agent can pause the workflow.

Your agents can use `bulk_enrich_companies` or `bulk_enrich_persons` to process lists of prospects. The framework handles the sequential execution, passing the enriched data between agents for final validation.

The crew will fail to initialize, but you can run `test_lusha_auth` to diagnose connection issues. This helper tool quickly verifies your API key status before your agents start their runs.

Yes, all direct dials, emails, and corporate profiles are routed through an encrypted tunnel directly to your local CrewAI runtime. The Vinkius MCP sandbox ensures that no external parties can intercept or log the contact details during execution.

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