How to Use the Ecomail MCP in Pydantic AI

Q: How do I attach the Ecomail MCP Server to Pydantic AI?

Initialize MCPToolset with your server URL. Pass that toolset into your Agent constructor. Do not use the old MCPServerHTTP class, as it is deprecated in current versions.

Q: Can Pydantic AI monitor my Ecomail list sizes?

Yes. The agent can run quickmarketingvolumeaudit to get a snapshot of your audience size. You can write a Pydantic model to enforce that the returned subscriber count is always an integer.

Q: What happens if the Ecomail API returns malformed data to Pydantic AI?

The framework throws a strict validation error. If listaddresslistsubscribers returns a string where you expected a boolean, the agent catches the mismatch before it tries to process the contact record.

Type-safe Ecomail API integration for Pydantic AI agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ecomail MCP to Pydantic AI

Create your Vinkius account to connect Ecomail 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 Ecomail with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict validation for Ecomail data

Marketing APIs return messy data. When you connect Ecomail to Pydantic AI via this MCP Server, every single response is validated at runtime. If the API drops a required field, your agent fails loudly instead of silently corrupting your database. You define the exact shape of a campaign report. When the agent calls `get_campaign_performance_details`, Pydantic AI checks the incoming JSON against your models. Bad data gets rejected immediately, keeping your agent's reasoning grounded in reality.

Audit templates with the MCP Server

Your agent can inspect your existing messaging setup without breaking anything. It uses `list_email_templates` to pull the raw HTML and subject lines of your current drafts directly into your Python environment. Because you are building with a framework that prioritizes correctness, you can trust the outputs. The agent can cross-reference those templates against your account limits using `get_ecomail_account_metadata` to ensure you have the capacity to send the next batch.

Track subscriber movement accurately

Finding specific users in a massive database requires precision. Your agent executes `search_marketing_subscribers` to locate contacts, and Pydantic AI ensures the returned email addresses actually look like email addresses. Once located, the agent pulls the detailed history with `get_subscriber_profile`. You set this up by passing your Vinkius endpoint into `MCPToolset` and attaching it to your agent. No deprecated HTTP wrappers, just clean streamable connections.

Setup guide

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

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

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

Initialize `MCPToolset` with your server URL. Pass that toolset into your Agent constructor. Do not use the old `MCPServerHTTP` class, as it is deprecated in current versions.

Yes. The agent can run `quick_marketing_volume_audit` to get a snapshot of your audience size. You can write a Pydantic model to enforce that the returned subscriber count is always an integer.

The framework throws a strict validation error. If `list_address_list_subscribers` returns a string where you expected a boolean, the agent catches the mismatch before it tries to process the contact record.

Yes. The framework is model-agnostic. You can run a local model via Ollama, connect it to the MCP Server, and have it analyze `list_latest_marketing_campaigns` without sending your prompts to a closed-source provider.

Your account usage limits and API metadata are transmitted through a strictly authenticated, ephemeral tunnel. The Vinkius platform requires a single endpoint token to connect, ensuring that no unauthorized client can access your Pydantic AI data stream.

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