How to Use the Postscript MCP in Pydantic AI

Q: How do I add the Postscript server to Pydantic AI?

Install the slim package with MCP support, then use the MCPToolset class to register your server URL. Pass it to your agent's toolsets list to start using the tools.

Build type-safe SMS marketing agents for Shopify using Pydantic AI and Postscript.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Postscript MCP to Pydantic AI

Create your Vinkius account to connect Postscript to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Postscript with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate subscriber updates with Pydantic AI

Every response from `get_subscriber` or `create_subscriber` is strictly validated against your data models. If the API returns malformed data, the process fails immediately. This prevents silent errors where bad data might otherwise trigger broken SMS sequences. You get reliable, predictable behavior every time the agent communicates with the server.

Execute type-safe marketing actions

Your agent uses `list_automations` and `list_campaigns` to build its context. Pydantic AI ensures that the returned objects map perfectly to your internal logic. This creates a robust foundation for automated messaging. You know exactly what fields are available because the framework enforces your schema at runtime.

Manage server webhooks with strict types

Control your integration events using `create_webhook` and `delete_webhook`. The agent validates all input parameters before sending them to the server. This eliminates common errors like missing fields or incorrect data types. Your webhook management becomes a clean, type-checked part of your codebase.

Setup guide

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

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

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

If an MCP tool returns unexpected data, the framework raises a validation error. This forces the agent to handle the failure rather than hallucinating or continuing with bad input.

Yes, the toolset is model-agnostic. You can switch between different LLMs, and your integration logic remains consistent thanks to the underlying type validation.

Install the slim package with MCP support, then use the `MCPToolset` class to register your server URL. Pass it to your agent's toolsets list to start using the tools.

You should. Defining Pydantic models for subscriber and campaign data allows the agent to interact with your store information with full IDE autocompletion and type safety.

Your contact data remains encrypted during transit via the MCP protocol. Because Pydantic AI validates every packet, unauthorized or improperly formatted data is rejected before it ever reaches your application logic.

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