How do I create a Polar Personal Access Token?

Log in to the [**Polar Dashboard**](https://polar.sh), go to **Settings > Developer > Personal Access Tokens**, click **Create Token**, give it a name and copy the token immediately — it starts with `polar_pat_` and won't be shown again.

Can I check my subscription revenue?

Yes! Use `list_subscriptions` with status 'active' to see all active subscriptions, and `list_orders` to see completed orders with their amounts. Combine both to get a full picture of your recurring and one-time revenue.

Can I create checkout links programmatically?

Yes! Use `create_checkout` with a product_id and optionally a customer_id and discount_id. This creates a checkout session that returns a URL you can share with customers or embed in your app.

Polar MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Polar
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Polar through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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 Polar "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Polar?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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 Polar MCP Server

Connect your Polar account to any AI agent and take full control of your digital commerce operations through natural conversation.

Pydantic AI validates every Polar tool response against typed schemas, catching data inconsistencies at build time. Connect 10 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

Product Management — List, retrieve and audit all products (one-time, subscription, free) with pricing and metadata
Subscription Tracking — Monitor active, canceled and past_due subscriptions with billing periods and customer info
Order & Revenue — List completed orders with amounts, currency, payment status and customer details
Customer Discovery — Browse customers by email, name and purchase history
Discount Management — List, create and audit discount codes with percentage or fixed-amount types
Checkout Operations — Create checkout sessions for products and track open, expired and confirmed checkouts
Webhook Audit — Review configured webhook endpoints and their subscribed events

The Polar MCP Server exposes 10 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.

How to Connect Polar to Pydantic AI via MCP

Follow these steps to integrate the Polar MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from Polar with type-safe schemas

Why Use Pydantic AI with the Polar MCP Server

Pydantic AI provides unique advantages when paired with Polar 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 Polar integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Polar connection logic from agent behavior for testable, maintainable code

Polar + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Polar MCP Server delivers measurable value.

Type-safe data pipelines: query Polar with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Polar tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Polar and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Polar responses and write comprehensive agent tests

Polar MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Polar to Pydantic AI via MCP:

create_checkout

Requires the product ID. Optionally associate with an existing customer and apply a discount. Returns the checkout session with its URL that you can redirect customers to for payment. Create a new checkout session in Polar

create_discount

Requires the name, code, type (percentage or fixed_amount), and amount. Optionally set the duration (once, forever, repeating). The discount can be applied during checkout. Create a new discount code in Polar

get_product

Provide the product ID (UUID format). Get details for a specific Polar product

list_checkouts

Each checkout shows its status (open, expired, confirmed), associated product, customer, and creation date. Useful for tracking abandoned and completed checkouts. List checkout sessions in your Polar store

list_customers

Each customer shows their email, name, billing address, and metadata. Optionally filter by email to find a specific customer. List customers in your Polar store

list_discounts

Each discount shows its code, type (percentage, fixed_amount), amount, duration (once, forever, repeating), and active status. Use this to audit your promotional offers. List discount codes in your Polar store

list_orders

Each order shows the customer, product, amount, currency, payment status, and creation date. Useful for tracking revenue and verifying successful transactions. List orders in your Polar store

list_products

Each product includes its name, description, price, type (one-time, subscription, free), and metadata. Use this to audit your product catalog and see what you are selling. List products in your Polar store

list_subscriptions

Each subscription shows the customer, product, status (active, past_due, canceled, expired, incomplete, trialing), current period start/end dates, and amount. Optionally filter by status and set a limit. List subscriptions in your Polar store

list_webhooks

Each webhook shows its URL, subscribed events (order.created, subscription.active, etc.), and status. Use this to audit your event integrations. List webhook endpoints in your Polar store

Example Prompts for Polar in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Polar immediately.

"Show me all active subscriptions and their total monthly revenue."

"Create a 20% discount code called 'LAUNCH20' for the summer sale."

"Show me all orders from the last 30 days."

Troubleshooting Polar MCP Server with Pydantic AI

Common issues when connecting Polar to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Polar + Pydantic AI FAQ

Common questions about integrating Polar MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Polar MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.