How to Use the UniOne MCP in Pydantic AI

Q: Can I use UniOne to track my sends with Pydantic AI?

You can list suppressed emails using listsuppression. This gives your agent a validated record of blocked addresses, letting you build a clean target list for the next run.

Send high-deliverability emails and manage campaigns using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect UniOne MCP to Pydantic AI

Create your Vinkius account to connect UniOne 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 UniOne with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Email Campaigns via MCP Server

The `list_templates` tool lets your agent see all available email templates. You can check if you're using the right one before sending out anything. Need to change a template? The `set_template` tool creates or updates them instantly, making sure your agents always reference current branding.

Send Emails from Pydantic AI

Agents can send emails using the `send_email` tool. This is for single, transactional messages—think confirmation alerts or status updates. If you're running a campaign, use `send_template`. It takes an existing template and executes the send, keeping all your outputs strictly typed.

Maintain Email Infrastructure

Keep your system clean with tools like `list_webhooks` and `get_webhook`. You can check if a webhook is set up correctly to catch delivery data. If something breaks, the `delete_webhook` tool lets your agent scrub old or broken endpoint configurations.

Setup guide

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

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

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

UniOne connects via a streamable HTTP interface, which is the unified approach you prefer. Since every response from this MCP Server passes through Pydantic validation, your agent gets guaranteed data correctness.

It handles millions of messages. The server manages the heavy lifting of deliverability and analytics so that even massive campaigns return predictable, type-safe results to your agent.

The server handles email templates, webhooks configurations, and suppression lists. Because everything is validated against a schema, you never have to worry about unexpected or corrupt fields in that operational data.

You can list suppressed emails using `list_suppression`. This gives your agent a validated record of blocked addresses, letting you build a clean target list for the next run.

The server manages email sending and campaign metadata. Your agent works on validated records of templates and suppression lists, ensuring that all actions are predictable and type-checked.

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