How to Use the ActiveCampaign MCP in Pydantic AI

Q: What's the setup for using ActiveCampaign with Pydantic AI?

It's one line. You create an MCPToolset instance with your Vinkius server URL and pass it to your Pydantic AI Agent. The framework handles discovery and validation of the ActiveCampaign tools automatically.

Get type-safe access to your ActiveCampaign data in Python with Pydantic AI. No more guessing at API schemas.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ActiveCampaign MCP to Pydantic AI

Create your Vinkius account to connect ActiveCampaign 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 ActiveCampaign with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create Contacts with Runtime Validation

This toolset lets your agent create new contacts in your CRM. When your agent calls `create_contact`, the JSON response from ActiveCampaign is immediately parsed and validated against a Pydantic model. If the API returns an unexpected field or a missing ID, your code raises a `ValidationError` on the spot. You find out about data issues immediately, not three weeks later when a nurture sequence fails. It's about writing code that doesn't silently break.

Pull CRM Data You Can Actually Trust

When your agent gets data using `list_contacts` or `list_deals`, you know the structure is correct. Pydantic AI forces every record into a strict schema before your agent's code can even touch it. This means no more defensive coding, no more `try/except` blocks around every dictionary access. You can trust that `contact.email` exists and is a string because the Pydantic model already confirmed it. This MCP Server gives you that guarantee for your ActiveCampaign data.

Model-Agnostic CRM Management

Use any LLM you want—OpenAI, Anthropic, Gemini, or a local model. Pydantic AI handles the tool-calling logic. Your agent decides to run `add_tag_to_contact`, and Pydantic AI ensures the call is structured correctly for this MCP Server. This separates your application logic from the specific model you're using. You can swap out your LLM without rewriting all your ActiveCampaign integration code. The Pydantic models and the toolset provide a stable contract.

Setup guide

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

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

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

It fails loudly, which is what you want. If ActiveCampaign changes a field name in the data returned by `list_deals`, Pydantic AI will raise a `ValidationError` because the response no longer matches the model. This prevents bad data from getting into your system.

It's one line. You create an `MCPToolset` instance with your Vinkius server URL and pass it to your Pydantic AI `Agent`. The framework handles discovery and validation of the ActiveCampaign tools automatically.

Yes. Pydantic AI is model-agnostic. As long as your local model supports function calling, you can connect it to this toolset to manage your ActiveCampaign contacts and deals. The validation happens regardless of which LLM you use.

No, it's about correctness, not speed. The Pydantic validation adds a tiny bit of overhead to each call. You trade a few milliseconds for the guarantee that the data your agent is working with is always correctly structured.

The server processes your ActiveCampaign contact records and deal information. Pydantic AI itself doesn't store anything. The Vinkius platform, which runs the server, uses ephemeral sandboxes for each request, meaning your data is wiped after the call completes. Nothing is logged or stored.

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