How to Use the ActiveTrail MCP in Pydantic AI

Q: How does the agent handle the list of campaigns?

The agent calls listcampaigns to get drafts and sent items. Pydantic AI parses the JSON response into typed models, making it easy for your agent to safely inspect subject lines and send dates.

Get type-safe ActiveTrail marketing automation with strict 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 ActiveTrail MCP to Pydantic AI

Create your Vinkius account to connect ActiveTrail 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 ActiveTrail with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe contact creation with Pydantic AI

The `create_contact` tool ensures that your agent can only write valid subscriber data to ActiveTrail. By using this MCP Server, every contact field returned or sent is validated against strict Python types at runtime. If the agent attempts to pass a malformed email or missing field, the framework raises an immediate validation error. This prevents corrupted data from ever reaching your ActiveTrail database, keeping your lists clean.

Safe campaign parsing with Pydantic AI

The `list_campaigns` tool returns a structured list of your sent and draft emails. The MCP Server outputs this data, and Pydantic AI validates the structure before your agent can read it. If ActiveTrail changes its API response structure, your code fails loudly and explicitly. You will never have to debug silent failures or hallucinated campaign IDs because the types are enforced at the network boundary.

Type-guaranteed SMS notifications

The `send_sms` tool requires a valid phone number and message body to execute. When your agent decides to send an SMS, Pydantic AI checks that these arguments conform to the expected schema before making the network call. This type-safety is model-agnostic. Whether you run your agent on GPT-4, Claude, or a local Llama model, the validation happens in Python, ensuring consistent behavior across any LLM backend.

Setup guide

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

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

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

Use the MCPToolset class pointing to your Vinkius HTTP URL. Pass this toolset instance inside the toolsets list when initializing your Pydantic AI Agent.

The framework will raise a validation error at runtime. This guarantees that your agent never processes corrupt contact or campaign data, protecting your application from silent bugs.

Yes, the tool validation happens at the Python level. You can use any supported LLM, and Pydantic AI will enforce the ActiveTrail tool schemas identically across all of them.

The agent calls list_campaigns to get drafts and sent items. Pydantic AI parses the JSON response into typed models, making it easy for your agent to safely inspect subject lines and send dates.

Your ActiveTrail subscriber lists are accessed through an ephemeral V8 sandbox managed by Vinkius. The data is validated locally in your Python environment and is never cached or stored on external servers.

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