How to Use the Leadfeeder MCP in Pydantic AI

Q: How do I register the Leadfeeder server in Pydantic AI?

Instantiate an MCPToolset with the MCP HTTP endpoint provided by Vinkius to connect Leadfeeder to Pydantic AI. Pass this toolset into your Pydantic AI Agent constructor to give your model immediate access to Leadfeeder's listleads tool.

Q: Does this Leadfeeder MCP Server support the deprecated MCPServerHTTP class in Pydantic AI?

No, you should use the unified MCPToolset class for all HTTP and SSE connections when linking Leadfeeder to Pydantic AI. This is the recommended approach for modern Pydantic AI installations connecting to Leadfeeder.

Q: Can I fetch aggregate Leadfeeder visit metrics safely using Pydantic AI?

Yes, you can call listaccountvisits to retrieve high-level Leadfeeder traffic stats within your Pydantic AI agent. The tool output is structured so your Pydantic AI agent can easily parse Leadfeeder pageviews without manual regex.

Bring strict type safety to your Leadfeeder workflows with Pydantic AI for bulletproof lead enrichment.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Leadfeeder MCP to Pydantic AI

Create your Vinkius account to connect Leadfeeder 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 Leadfeeder with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Leadfeeder data with Pydantic AI

Don't let malformed API responses break your Pydantic AI pipelines when fetching Leadfeeder data. By using Pydantic AI, every Leadfeeder payload returned by `get_lead` is validated against strict schemas before your agent even sees it. If Leadfeeder returns an unexpected null, Pydantic AI catches it instantly so your code doesn't crash. This ensures your sales team only gets clean Leadfeeder data inside your Pydantic AI application.

Track Leadfeeder visits securely with this MCP Server

When monitoring web traffic with Pydantic AI, you need to know exactly which Leadfeeder companies are on your site. This MCP Server lets your Pydantic AI agent call `list_lead_visits` to fetch structured Leadfeeder session data for any target company. The Pydantic AI framework validates the session timestamps and page URLs returned by the Leadfeeder API. This guarantees that your Pydantic AI agent triggers outbound emails based on actual, verified Leadfeeder browsing behavior.

Pull typed Leadfeeder custom feeds via Pydantic AI

Parsing custom Leadfeeder filters can be messy in a Pydantic AI app. Your Pydantic AI agent can use `list_custom_feeds` to discover active Leadfeeder segments and then query them using `get_custom_feed`. Every Leadfeeder filter rule is cast into a typed Python model inside Pydantic AI. This makes it incredibly easy to write downstream Pydantic AI logic that routes Leadfeeder leads based on specific industry codes.

Setup guide

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

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

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

Instantiate an `MCPToolset` with the MCP HTTP endpoint provided by Vinkius to connect Leadfeeder to Pydantic AI. Pass this toolset into your Pydantic AI `Agent` constructor to give your model immediate access to Leadfeeder's `list_leads` tool.

Pydantic AI will raise a validation error at runtime rather than letting your agent hallucinate empty Leadfeeder fields. This ensures your Leadfeeder data pipelines remain completely predictable and type-safe within Pydantic AI.

No, you should use the unified `MCPToolset` class for all HTTP and SSE connections when linking Leadfeeder to Pydantic AI. This is the recommended approach for modern Pydantic AI installations connecting to Leadfeeder.

Yes, you can call `list_account_visits` to retrieve high-level Leadfeeder traffic stats within your Pydantic AI agent. The tool output is structured so your Pydantic AI agent can easily parse Leadfeeder pageviews without manual regex.

Your API token and Leadfeeder account IDs are encrypted in transit and only injected into the ephemeral V8 isolate during Pydantic AI runs. No sensitive Leadfeeder data's ever cached or exposed to external networks by your Pydantic AI toolset.

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