How to Use the FunnelCockpit MCP in Pydantic AI

Q: How do I set up FunnelCockpit with Pydantic AI?

Install pydantic-ai-slimmcp, then use MCPToolset with your Vinkius server URL. Pass the toolset directly into your agent's toolsets parameter.

Q: How does Pydantic AI handle unexpected schema changes in my FunnelCockpit funnels?

When the agent calls getfunnel, the framework validates the response. If the marketing platform updates its API payload, Pydantic AI raises a validation error to prevent silent data corruption.

Q: Can I update contact records safely with this MCP Server?

Yes, you can run updatecontact with a JSON string of field-value pairs. The agent validates the input schema before sending the payload to ensure data integrity.

Q: How do I retrieve a specific contact's details?

Use getcontact with the target contact ID through the MCP Server. The agent fetches the CRM profile and parses it into a typed Pydantic model for safe handling.

Build type-safe marketing pipelines that validate every FunnelCockpit API response using Pydantic AI and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FunnelCockpit MCP to Pydantic AI

Create your Vinkius account to connect FunnelCockpit 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 FunnelCockpit with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate CRM data with this MCP Server

The `create_contact` tool adds new leads to your marketing CRM with strict runtime type checks. Pydantic AI intercepts the server response, verifying that the returned contact ID and email match your exact schema. If the API returns unexpected data formats, the framework raises a validation error immediately. This prevents corrupted records from breaking your downstream email sequences or lead assignment code.

Inspect funnel layouts using Pydantic AI

The `get_funnel` tool pulls structured funnel data directly into your type-safe agent. The agent uses `list_funnels` to locate the target campaign and `list_pages` to verify the page order against your Pydantic models. This architecture guarantees that your agent only works with valid page structures. If a funnel layout changes unexpectedly, the agent halts execution instead of processing broken links or missing steps.

Validate status and campaigns via MCP

The `check_funnelcockpit_status` tool verifies API availability before your agent executes critical database writes. The agent runs `get_account` to pull profile details, validating the response against your internal subscription schemas. This approach ensures your agent never attempts to trigger campaigns when your account limits are reached. By checking `list_campaigns` first, the agent confirms the target sequence exists before attempting to enroll new contacts.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]`, then use `MCPToolset` with your Vinkius server URL. Pass the toolset directly into your agent's `toolsets` parameter.

When the agent calls `get_funnel`, the framework validates the response. If the marketing platform updates its API payload, Pydantic AI raises a validation error to prevent silent data corruption.

Yes, you can run `update_contact` with a JSON string of field-value pairs. The agent validates the input schema before sending the payload to ensure data integrity.

Use `get_contact` with the target contact ID through the MCP Server. The agent fetches the CRM profile and parses it into a typed Pydantic model for safe handling.

Your CRM contact data is processed in ephemeral V8 isolates on Vinkius. Security credentials are injected at runtime, so your local Pydantic AI agent never handles raw, unencrypted API keys.

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