How to Use the Courier MCP in Pydantic AI

Use Pydantic AI with Courier to ensure every notification action is type-safe and validated at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Courier MCP to Pydantic AI

Create your Vinkius account to connect Courier 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 Courier with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Courier responses in Pydantic AI

Every response from `list_messages` or `get_message_details` is checked against Pydantic models. If the schema shifts, the agent stops immediately. You avoid silent failures common in standard API integrations. It keeps your notification logic predictable and bug-free.

Manage templates via MCP Server

The `list_templates` tool lets your agent query available notification formats. You get a clean list of IDs and channels for every message you want to send. Your agent uses these validated templates to construct outgoing alerts. It prevents errors caused by missing or outdated template configurations.

Automate message status checks

Your agent uses `list_messages` to track status updates for recent notifications. It confirms if messages were delivered or clicked without manual intervention. This process provides a clear view of your engagement metrics. You get accurate, typed data for every notification event.

Setup guide

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

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

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

Yes, every tool response is validated against your Pydantic models. You get an immediate error if the API returns unexpected data formats.

You define the MCPToolset with your server URL and pass it to the agent. It creates a seamless bridge between your type-safe agent and the Courier API.

It provides a robust way to handle subscription lists. The agent validates all input and output, ensuring list IDs and counts are always correct.

Yes, the server supports SSE and Streamable HTTP. You choose the transport that fits your local or remote development needs.

Your notification metadata is parsed and validated by your local agent process. We ensure no unauthorized data leaks by keeping the validation logic strictly within your runtime.

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