How to Use the Lago MCP in Pydantic AI

Q: How does Pydantic AI validate billing events sent to Lago?

The framework inspects the arguments passed to sendevent against its internal schemas. It rejects any payload with missing or incorrectly typed fields before hitting the API.

Q: Can I use Pydantic AI to safely manage Lago subscriptions?

Yes, the agent calls getsubscription and parses the response into a validated Python model. This ensures your application logic never processes malformed subscription data.

Connect Lago to Pydantic AI for type-safe usage-based billing, validating every event and subscription 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 Lago MCP to Pydantic AI

Create your Vinkius account to connect Lago 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 Lago with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Billable Metric Generation

The `create_billable_metric` tool defines your pricing dimensions with strict schema enforcement over our MCP server connection. Pydantic AI validates the metric's aggregation rules and event properties before making the API call, preventing runtime errors. If your agent attempts to pass an invalid aggregation type, the framework halts execution immediately. This strict validation guarantees that your billing configuration in Lago always matches your codebase models.

Guaranteed Event Ingestion via MCP Server

The `send_event` tool transmits single usage events to your billing pipeline. Pydantic AI enforces type safety on the event payload, ensuring that dimensions like customer IDs and numerical usage values are correctly formatted. For bulk operations, the agent uses `batch_events` to send multiple records simultaneously. If any event in the batch violates your Pydantic models, the SDK blocks the entire call to keep your data clean.

Automated Customer Lifecycle Management

The `upsert_customer` tool manages your customer records with strict field validation. Your agent executes this tool to register new accounts, immediately followed by `create_subscription` to assign them to a billing plan. To apply promotional codes, the agent calls `apply_coupon` with validated coupon IDs. The entire sequence runs within your type-safe agent loop, failing loudly if any external API response deviates from your expected Pydantic schemas.

Setup guide

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

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

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

The framework inspects the arguments passed to `send_event` against its internal schemas. It rejects any payload with missing or incorrectly typed fields before hitting the API.

Yes, the agent calls `get_subscription` and parses the response into a validated Python model. This ensures your application logic never processes malformed subscription data.

The SDK raises a validation error immediately, halting the execution flow. This prevents your agent from making decisions based on corrupted billing or invoice data.

You initialize the MCPToolset with your Vinkius HTTP endpoint. Pass this toolset directly to your agent's constructor to enable all 12 billing tools.

Vinkius routes all traffic to this MCP server through transient V8 Isolates. Your customer records, subscription details, and API tokens are never written to disk, ensuring complete data isolation.

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