How to Use the CUFinder MCP in Pydantic AI

Q: How do I add CUFinder to my Pydantic AI project?

Install the slim package, create an MCPToolset pointing to the server, and pass it to your agent. All 13 tools become available for use immediately.

Use CUFinder with Pydantic AI for type-safe B2B lead discovery and strictly validated agent responses.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CUFinder MCP to Pydantic AI

Create your Vinkius account to connect CUFinder 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 CUFinder with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe tool calls with Pydantic AI

Every response from the MCP Server undergoes runtime validation against your Pydantic models. If `find_email` returns malformed data, your agent raises a validation error immediately. This prevents silent failures during your prospecting runs. You define exactly what the data should look like, and the framework forces compliance.

Enrich leads using Pydantic AI

Integrate `enrich_linkedin` or `find_phone` into your agent logic with complete confidence in the data structure. The framework ensures the output matches your expected schema. You build robust prospecting flows that handle missing fields gracefully. The agent fails early if the API returns unexpected content, keeping your data clean.

Configure your MCP Server for Pydantic AI

Initialize your `MCPToolset` with the server URL to connect. This approach handles the communication between your agent and the external server using standard transport protocols. Your agent treats the tools as first-class citizens. You get auto-completion and type checking during development, which catches bugs before you run your first query.

Setup guide

Set up CUFinder 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": {
        "cufinder-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent CUFinder 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 CUFinder. 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 CUFinder 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 CUFinder MCP in Pydantic AI

You get strict type validation for every piece of data retrieved. If `get_company_revenue` returns an unexpected format, the agent stops instead of propagating bad data.

Yes, you define your Pydantic models, and the framework validates the tool output automatically. It is the safest way to ingest external business data.

Install the slim package, create an `MCPToolset` pointing to the server, and pass it to your agent. All 13 tools become available for use immediately.

Your agent only sends the necessary lookup parameters. The Vinkius sandbox ensures your session is ephemeral and isolated from other users.

It touches B2B contact data, including email addresses, phone numbers, and company metadata. All fields are validated against your schema upon arrival.

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