How to Use the MailerLite MCP in Pydantic AI

Q: How do I integrate MailerLite with Pydantic AI?

Install the pydantic-ai-slimmcp package and initialize MCPToolset with your HTTP endpoint. Pass this toolset directly to your Agent instance. Note that the older MCPServerHTTP method is deprecated.

Q: Can Pydantic AI manage MailerLite popups?

Your agent can pull popup configurations by calling listforms. The framework validates the returned form types and IDs. You can then safely use those IDs in subsequent routing logic.

Enforce strict runtime validation on all MailerLite marketing data using Pydantic AI to prevent silent corruption in your agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MailerLite MCP to Pydantic AI

Create your Vinkius account to connect MailerLite 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 MailerLite with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe MailerLite subscriber creation

MailerLite demands precise payloads, particularly the mandatory email field. Pydantic AI guarantees that your agent never sends a malformed MCP request to `create_subscriber`. If the LLM hallucinates a missing email, the framework throws a validation error before the API call even fires. Reading data gets the exact same strict treatment. When you call `get_subscriber`, the returned JSON must match your defined Pydantic models. You never have to worry about unexpected null values breaking your downstream marketing logic.

Validated MCP Server campaign fetching

Pulling analytics requires absolute trust in the returned data structure. Your agent triggers `list_campaigns` to grab performance metrics, and Pydantic AI validates every single integer and string. Bad data fails loudly instead of silently poisoning your reporting dashboard. Complex filtering works flawlessly under this model. You can instruct the agent to run `list_subscribers` targeting only bounced or junk statuses. The framework ensures the status enum matches exactly what the MailerLite API expects.

Strict group and segment routing

Moving users between lists is a high-risk operation for domain reputation. When your agent executes `add_subscriber_to_group` or `remove_subscriber_from_group`, it strictly validates the subscriber ID and group ID types. This prevents users from being dumped into the wrong promotional sequence. Discovering targets is equally bulletproof. The agent calls `list_groups` or `list_segments` to map out the current account structure. Because Pydantic AI is model-agnostic, you can swap between Anthropic and local models without changing a single line of this validation logic.

Setup guide

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

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

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

Install the pydantic-ai-slim[mcp] package and initialize MCPToolset with your HTTP endpoint. Pass this toolset directly to your Agent instance. Note that the older MCPServerHTTP method is deprecated.

Yes, missing mandatory fields trigger immediate loud failures. The `create_subscriber` tool strictly requires an email address. If the LLM omits it, the framework blocks the execution and returns a clear type error.

Your agent can pull popup configurations by calling `list_forms`. The framework validates the returned form types and IDs. You can then safely use those IDs in subsequent routing logic.

The framework natively handles both Streamable HTTP and SSE transports. You simply provide the correct endpoint URL to the toolset. The underlying client manages the connection lifecycle automatically.

Fetching subscriber profiles exposes raw email addresses and engagement metrics to your application. Vinkius secures this by running the connection through an ephemeral, zero-trust V8 sandbox. The environment spins up solely for your validated request and immediately destroys itself afterward.

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