How to Use the Emarsys MCP in Pydantic AI

Q: Is it possible to list all Emarsys forms and trigger events with a Pydantic AI agent?

Absolutely. Your agent can use the listregistrationforms and listtriggerevents tools. Pydantic AI ensures the returned lists and their contents are correctly typed.

Build type-safe Emarsys agents that won't fail silently. Pydantic AI guarantees your data is what you expect it to be.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Emarsys MCP to Pydantic AI

Create your Vinkius account to connect Emarsys 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 Emarsys with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit Campaigns with Guaranteed Data Types

Let's be real, APIs change. With Pydantic AI, that's no longer your problem. When your agent calls `get_campaign_details` or `list_email_campaigns`, the response is parsed and validated against a Pydantic model before your code ever sees it. If the Emarsys API returns an unexpected field or a string instead of an integer, your agent doesn't process bad data. It throws a `ValidationError`. You get immediate, loud feedback that something is wrong, preventing silent data corruption downstream.

Validate Your Marketing Funnels

You can build an agent that does more than just fetch data—it validates it. Have your agent check your automation flows with `list_automation_programs` and your target groups with `list_audience_segments`. The data is guaranteed to match the schema. This is about building reliable systems. If a critical automation program is missing a required field in the API response, you'll know instantly. It's the difference between a robust monitoring agent and a script that might break at any time.

Use Any LLM with This MCP Server

Pydantic AI is model-agnostic. You can use OpenAI, a local Llama model, or anything in between. This Emarsys MCP Server provides the tools, and Pydantic AI provides the safe connection to whichever brain you choose for your agent. Your agent can map out your entire lead capture process by calling `list_registration_forms` and `list_trigger_events`. It gets a full picture of your setup, and you get peace of mind knowing every piece of data has been validated.

Setup guide

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

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

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

It validates every API response from this server against a strict Pydantic model at runtime. If the data doesn't match the expected schema, your code gets a `ValidationError` instead of corrupted data.

Yes. Pydantic AI is model-agnostic. You can configure it to use a local LLM to drive the agent, which then calls the `list_email_campaigns` tool on this Emarsys server.

Your agent will fail loudly with a validation error on the first call that receives an unexpected data structure. This protects your application from silent failures caused by upstream API changes.

Absolutely. Your agent can use the `list_registration_forms` and `list_trigger_events` tools. Pydantic AI ensures the returned lists and their contents are correctly typed.

This server is limited to read-only access for campaign and list metadata. Access is controlled through Vinkius's auth system, where your Pydantic AI agent uses a single, dedicated endpoint token for all its requests.

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