How to Use the MoonClerk MCP in Pydantic AI

Q: How do I fetch payments for a specific customer?

Your agent can call listpayments and filter the results by the customer's unique identifier. The returned data contains exact transaction records and payment statuses.

Validate MoonClerk customer records and subscription states at runtime using Pydantic AI type-safe agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MoonClerk MCP to Pydantic AI

Create your Vinkius account to connect MoonClerk 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 MoonClerk with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe customer lookups

The `get_customer` tool in this MCP server returns raw JSON profiles that Pydantic AI automatically validates against strict Python type models. If the API payload contains unexpected fields or missing schemas, the runtime raises a validation error instead of passing dirty data to your model. This strict typing prevents your agent from hallucinating customer emails or processing corrupted metadata. You define the exact structure you expect, and the framework guarantees the tool output matches it before the model ever sees it.

Validate subscription states at runtime

Your agent uses `list_subscriptions` to check active agreements without risk of silent data corruption. Because Pydantic AI is model-agnostic, you can use this toolset with any LLM while keeping validation logic entirely local. If you need to drill down into a single account, the agent calls `get_subscription` to fetch specific tier limits. The framework parses the response fields into Python dataclasses, making it simple to write assertions around billing dates.

Verify checkout forms and pricing plans

The `list_forms` tool exposes active checkout setups for your agent to review. Pydantic AI ensures that every returned form URL and pricing field adheres to your predefined schema. When validating plans, the agent invokes `get_plan` to inspect billing frequencies and trial periods. This guarantees that your agent only recommends active, correctly priced checkout links to users.

Setup guide

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

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

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

Use the unified MCPToolset class with your Vinkius HTTP endpoint. Pass this toolset directly to your Pydantic AI Agent instance to expose endpoints like `list_payments` to your model.

The framework will raise a validation error at runtime, preventing the agent from acting on corrupt subscription or customer fields. This ensures absolute correctness for your financial workflows.

Yes, the framework is model-agnostic. Your local LLM can invoke tools like `list_plans` and `get_plan` as long as the model supports tool calling.

Your agent can call `list_payments` and filter the results by the customer's unique identifier. The returned data contains exact transaction records and payment statuses.

The MCP server operates within a zero-trust V8 isolate that handles all API requests ephemerally. Your customer records and billing tokens are processed in memory and never written to persistent storage.

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