How to Use the EmailOctopus MCP in Pydantic AI

Q: How do I use the EmailOctopus tools with Pydantic AI?

Install the framework with pip install "pydantic-ai-slimmcp". Then, create an MCPToolset instance with your Vinkius server URL and pass that toolset into your Pydantic AI Agent.

Q: What happens if the EmailOctopus API returns an unexpected value with Pydantic AI?

Pydantic AI will raise a ValidationError. This is its main job—it protects your application from unexpected API changes or malformed data from tools like getcampaigndetails.

Q: Can a Pydantic AI agent audit my EmailOctopus lists?

Yes. Your agent can use listmarketinglists to find all your lists and getlistdetails to check their subscriber counts. You get the added guarantee that all the returned data conforms to your Pydantic models.

Get type-safe, validated EmailOctopus data in your Python app with Pydantic AI and stop worrying about API drift.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect EmailOctopus MCP to Pydantic AI

Create your Vinkius account to connect EmailOctopus 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 EmailOctopus with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Prevent Bad Data, Automatically

This server's tools return data that Pydantic AI validates against its models at runtime. If EmailOctopus ever changes an API field in `get_campaign_performance_summary`, your agent won't silently fail or process corrupt data. Instead, it will raise a `ValidationError` immediately. You'll know exactly what broke and where, so you can fix it without guessing.

A Model-Agnostic EmailOctopus MCP Server

Write your agent logic once, then run it with any LLM you want. Pydantic AI is model-agnostic, so you can swap between OpenAI, Anthropic, Gemini, or a local model without changing how you call `list_email_campaigns` or `get_contact_profile`. The `MCPToolset` handles the differences for you. This means you're not locked into a single model provider for your EmailOctopus automations.

Build Correctness-First Workflows

When correctness is the top priority, you need guarantees. When your agent uses `list_list_contacts` to get subscribers or `search_contacts_by_email` to find one, you can trust the structure of the data it gets back. There's no more need for defensive coding or wrapping every dictionary access in a `try/except` block just in case a key is missing. Pydantic AI handles the validation.

Setup guide

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

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

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

Install the framework with `pip install "pydantic-ai-slim[mcp]"`. Then, create an `MCPToolset` instance with your Vinkius server URL and pass that toolset into your Pydantic AI `Agent`.

Pydantic AI will raise a `ValidationError`. This is its main job—it protects your application from unexpected API changes or malformed data from tools like `get_campaign_details`.

Yes. Your agent can use `list_marketing_lists` to find all your lists and `get_list_details` to check their subscriber counts. You get the added guarantee that all the returned data conforms to your Pydantic models.

Yes, it works out of the box with the standard Streamable HTTP and SSE transports. You just point the `MCPToolset` at the Vinkius URL and it handles the underlying connection details.

The server only touches the specific EmailOctopus data needed for a tool, like contact emails or campaign performance numbers. Vinkius isolates every request in its own ephemeral container, and your data is never written to disk or logged.

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