How to Use the Lusha MCP in Pydantic AI

Use Pydantic AI with Lusha to enforce strict data types on all your B2B contact intelligence lookups.

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 Pydantic AI

Create your Vinkius account to connect Lusha to Pydantic 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe Lusha integration for Pydantic AI

Every response from `enrich_person_info` gets validated against your Pydantic models at runtime. If the API returns malformed data, the agent stops immediately. This prevents your agent from hallucinating fields or passing corrupted contact info into your CRM. You get clean, verified data or a clear validation error.

Verified lead prospecting with Pydantic AI

Run `prospect_new_leads` and map the output directly to your schema. Pydantic AI ensures that every field, from phone numbers to job titles, matches your expected types. This is essential for production systems where bad data breaks the workflow. You trust the data because the framework enforces the structure.

Account oversight for Pydantic AI agents

Your agent tracks its own resource usage by calling `get_credit_balance` before execution. It validates the integer return against your budget model. If you run out of credits, the agent catches the validation error instead of failing mid-process. It makes your automated research pipeline predictable and stable.

Setup guide

Set up Lusha MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "lusha-alternative-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Lusha tools.",
)

result = await agent.run("List recent Lusha transactions")
print(result.output)

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 Pydantic AI

Because it enforces strict data validation. If the Lusha API returns an unexpected format, the agent fails immediately, preventing silent data corruption.

You use the MCPToolset class and point it to the HTTP endpoint of the server. It integrates into your agent's toolsets list as a native dependency.

Yes. Since Pydantic AI is model-agnostic, this MCP Server works whether you are using a local model or a hosted API.

Pydantic AI will throw a validation error if the record doesn't match your defined model. You can then write a handler to decide whether to skip the record or retry.

All contact info is processed in memory. The Vinkius sandbox ensures that your Lusha credentials and the data retrieved remain isolated from other processes.

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