How to Use the Convertlab MCP in Pydantic AI

Q: How do I install the Convertlab toolset in Pydantic AI?

Install the framework using pip install "pydantic-ai-slimmcp". Then import MCPToolset, initialize it with your Vinkius URL, and pass it to the toolsets argument of your Pydantic AI Agent. This exposes tools like listcustomers with runtime validation.

Q: How is marketing data secured when using Convertlab with Pydantic AI?

Marketing events and customer profiles queried via listevents are validated in your local memory space. Vinkius secures the connection using isolated V8 sandboxes and ephemeral tokens, ensuring no persistent storage of your customer records occurs outside your infrastructure.

Run type-safe marketing operations in Convertlab with Pydantic AI validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Convertlab MCP to Pydantic AI

Create your Vinkius account to connect Convertlab 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 Convertlab with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe customer creation with Pydantic AI

`create_customer` lets your Pydantic AI agent insert new records into the Convertlab DM Hub with strict runtime type checks. Every field returned by the tool is validated against Pydantic models before your Python code processes it. If the API returns unexpected data formats during a `get_customer` call, the framework raises a validation error immediately. This prevents corrupted marketing profiles from polluting your application database or downstream systems.

Validate campaign listings at runtime

`list_campaigns` fetches your active marketing initiatives and parses them into typed Python objects. Your agent uses `get_campaign` to safely inspect campaign performance, confident that every integer and string matches your schema. Because Pydantic AI is model-agnostic, you can use this toolset with Anthropic, OpenAI, or local models. The validation layer ensures that whichever model you choose, the output format from Convertlab tools remains completely consistent.

Query events and segments via MCP Server

`list_events` allows your agent to pull marketing event logs and validate the payload structures instantly. The agent maps these events to customer groups retrieved through `list_member_groups` for accurate targeting. This MCP Server integrates with Pydantic AI using the unified MCPToolset class. The agent queries `list_touchpoints` to analyze customer interactions, ensuring that null values or missing fields are caught at the application boundary.

Setup guide

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

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

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

Install the framework using pip install "pydantic-ai-slim[mcp]". Then import MCPToolset, initialize it with your Vinkius URL, and pass it to the toolsets argument of your Pydantic AI Agent. This exposes tools like `list_customers` with runtime validation.

The framework fails loudly by raising a validation error. If `get_campaign` returns a malformed date or missing campaign ID, Pydantic AI catches it at the boundary, preventing your agent from making decisions based on bad data.

Yes. You should use the unified MCPToolset class instead of the deprecated MCPServerHTTP class. This unified approach handles the Streamable HTTP connection to your Convertlab server hosted on Vinkius.

Yes. Pydantic AI is model-agnostic, meaning you can connect this server to local models running via Ollama. The local model can call `list_touchpoints` to process marketing data without sending information to external model providers.

Marketing events and customer profiles queried via `list_events` are validated in your local memory space. Vinkius secures the connection using isolated V8 sandboxes and ephemeral tokens, ensuring no persistent storage of your customer records occurs outside your infrastructure.

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