UniOne MCP Server for Pydantic AIGive Pydantic AI instant access to 12 tools to Delete Template, Delete Webhook, Get Template, and more
Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect UniOne through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.
Ask AI about this App Connector for Pydantic AI
The UniOne app connector for Pydantic AI is a standout in the Developer Tools category — giving your AI agent 12 tools to work with, ready to go from day one.
Vinkius delivers Streamable HTTP and SSE to any MCP client
import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
agent = Agent(
model="openai:gpt-4o",
mcp_servers=[server],
system_prompt=(
"You are an assistant with access to UniOne "
"(12 tools)."
),
)
result = await agent.run(
"What tools are available in UniOne?"
)
print(result.data)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About UniOne MCP Server
Connect your UniOne email delivery account to any AI agent and simplify how you manage your transactional messaging, email templates, and delivery tracking through natural conversation.
Pydantic AI validates every UniOne tool response against typed schemas, catching data inconsistencies at build time. Connect 12 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
What you can do
- Email Delivery — Send individual or bulk transactional emails with full HTML support and personalized sender details.
- Template Automation — List, create, and send emails using pre-defined templates for consistent branding.
- Event Monitoring — Configure webhooks and track delivery events (opened, clicked, delivered) in real-time.
- Reputation Management — List and manage suppressed email addresses (unsubscribes/bounces) to protect your sender score.
- Technical Control — Fetch detailed metadata for templates and webhooks directly from the agent.
The UniOne MCP Server exposes 12 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
All 12 UniOne tools available for Pydantic AI
When Pydantic AI connects to UniOne through Vinkius, your AI agent gets direct access to every tool listed below — spanning transactional-email, email-delivery, smtp, and more. Every call is secured with network, filesystem, subprocess, and code evaluation entitlements inside a sandboxed runtime. Beyond a simple connection, you get a full AI Gateway with real-time visibility into agent activity, enterprise governance, and optimized token usage.
Delete a template
Delete a webhook
Get template details
Get webhook details
List suppressed emails
List email templates
List webhooks
Send a transactional email
Send email using a template
Add email to suppression list
Create or update a template
Configure a webhook
Connect UniOne to Pydantic AI via MCP
Follow these steps to wire UniOne into Pydantic AI. The entire setup takes under two minutes — your credentials stay safe behind the Vinkius.
Install Pydantic AI
pip install pydantic-aiReplace the token
[YOUR_TOKEN_HERE] with your Vinkius tokenRun the agent
agent.py and run: python agent.pyExplore tools
Why Use Pydantic AI with the UniOne MCP Server
Pydantic AI provides unique advantages when paired with UniOne through the Model Context Protocol.
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your UniOne integration code
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
Dependency injection system cleanly separates your UniOne connection logic from agent behavior for testable, maintainable code
UniOne + Pydantic AI Use Cases
Practical scenarios where Pydantic AI combined with the UniOne MCP Server delivers measurable value.
Type-safe data pipelines: query UniOne with guaranteed response schemas, feeding validated data into downstream processing
API orchestration: chain multiple UniOne tool calls with Pydantic validation at each step to ensure data integrity end-to-end
Production monitoring: build validated alert agents that query UniOne and output structured, schema-compliant notifications
Testing and QA: use Pydantic AI's dependency injection to mock UniOne responses and write comprehensive agent tests
Example Prompts for UniOne in Pydantic AI
Ready-to-use prompts you can give your Pydantic AI agent to start working with UniOne immediately.
"List all email templates in my UniOne account."
"Send the 'welcome_01' template to 'user@example.com'."
"Check the suppression list for any recent bounces."
Troubleshooting UniOne MCP Server with Pydantic AI
Common issues when connecting UniOne to Pydantic AI through the Vinkius, and how to resolve them.
MCPServerHTTP not found
pip install --upgrade pydantic-aiUniOne + Pydantic AI FAQ
Common questions about integrating UniOne MCP Server with Pydantic AI.
How does Pydantic AI discover MCP tools?
MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.