How to Use the Recurly MCP in Pydantic AI

Run type-safe billing operations by validating Recurly data schemas with Pydantic AI 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 Recurly MCP to Pydantic AI

Create your Vinkius account to connect Recurly 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 Recurly with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe subscription checks with Pydantic AI

Silent data corruption is a nightmare for financial pipelines. Pydantic AI solves this by validating every response from `get_subscription_details` against strict Python types before your agent can use it. If Recurly updates its payload or an unexpected null value appears, the library raises a validation error immediately. This strict runtime validation means your agent never makes decisions based on garbled data. When looking up plans with `list_subscription_plans`, you can trust that every price, currency, and interval matches your exact schema expectations.

Bulletproof account creation via MCP Server

Creating customer records requires perfect input data. This MCP Server ensures that when your agent calls `create_billing_account`, the input parameters match Recurly's API requirements exactly. The Pydantic AI toolset intercepts invalid emails or missing billing addresses before sending the request. If the agent tries to use an invalid schema, the system catches the error locally. This keeps your Recurly logs clean and prevents your API rate limits from being wasted on bad requests.

Strict financial reporting validation

Financial reporting leaves no room for hallucinations. When your agent fetches billing history using `list_billing_invoices` or `get_revenue_summary`, Pydantic AI parses the dates and amounts into typed Python models. Your agent can then calculate metrics knowing the numbers are real. This approach works across any LLM provider you choose. It supports Anthropic, OpenAI, or local models while guaranteeing that outputs from `list_transactions` conform to your structures.

Setup guide

Set up Recurly 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": {
        "recurly-alternative-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Use the unified MCPToolset class pointing to your Vinkius HTTP endpoint. Pass this toolset instance directly into the toolsets list of your Agent constructor to expose all eleven billing tools.

The framework will raise a ValidationError at runtime, stopping the agent from processing the bad payload. This prevents silent failures and ensures your billing logic only acts on clean data.

No, the MCP server must be running externally. You connect to it over Streamable HTTP or SSE transports managed by Vinkius, which handles the live API connection to Recurly.

Yes, the older MCPServerHTTP class is deprecated. You should use the unified MCPToolset approach to connect your Recurly tools to your Python agents.

Security is handled at the transport layer where Vinkius runs your server in an ephemeral V8 sandbox. This prevents your customer profiles, plan details, and billing keys from being exposed to unauthorized processes.

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