How to Use the Lago MCP in OpenAI Agents SDK

Q: How do I handle failed billing event retries in Lago with the OpenAI Agents SDK?

Your agent catches execution errors during sendevent calls. You can configure a fallback agent to log the failed payload and retry using batchevents once connectivity stabilizes.

Q: Can the OpenAI Agents SDK automatically create customer accounts in Lago?

Yes, the agent invokes upsertcustomer using the customer's external ID during signup. It then runs createsubscription to assign them to a base tier.

Q: How does this Lago integration handle plan updates within the OpenAI Agents SDK?

The agent reads active subscriptions via getsubscription to verify current tiers. It then calls createplan to set up new pricing structures when your sales team updates contracts.

Connect Lago to your OpenAI Agents SDK to meter usage, manage subscriptions, and run billing workflows with built-in guardrails.

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 OpenAI Agents SDK

Create your Vinkius account to connect Lago to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Setup Metering with Built-in Guardrails

The `create_billable_metric` tool defines your pricing dimensions directly through your agent via the MCP server connection. Your OpenAI Agents SDK validates these metric definitions against your safety guardrails before execution, preventing accidental billing schema modifications. You avoid bad API states by letting the agent dry-run the metric setup. The agent then registers the metric, ensuring your production billing aligns with actual product usage.

High-Volume Event Ingestion via MCP Server

The `batch_events` tool handles high-volume usage ingestion by grouping raw events before transmission. Your agent coordinates this batching process, routing event payloads from your backend to Lago's ingestion pipeline. If an event fails, the agent uses `send_event` to retry individual payloads. The OpenAI dashboard traces these execution paths, giving you a clear audit trail of every billing event processed.

Automated Customer Onboarding and Plan Assignment

The `upsert_customer` tool creates or updates customer records in Lago based on your application's signup triggers. Your agent handles the handoff between onboarding flows and billing setup, immediately running `create_subscription` to attach the correct plan to the new user. To incentivize early adoption, the agent applies promotional discounts using `apply_coupon`. This entire lifecycle runs asynchronously within your python agent loop, keeping your core database free from complex billing logic.

Setup guide

Set up Lago MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Lago tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Lago tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Lago tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Lago Agent",
            instructions="You have access to Lago tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Your agent catches execution errors during `send_event` calls. You can configure a fallback agent to log the failed payload and retry using `batch_events` once connectivity stabilizes.

Yes, the agent invokes `upsert_customer` using the customer's external ID during signup. It then runs `create_subscription` to assign them to a base tier.

The agent reads active subscriptions via `get_subscription` to verify current tiers. It then calls `create_plan` to set up new pricing structures when your sales team updates contracts.

No, the SDK auto-discovers all 12 tools and applies your configured guardrails. This prevents the agent from executing unauthorized commands like `create_wallet` without explicit clearance.

Vinkius runs this MCP server in a zero-trust, ephemeral V8 Isolate sandbox. Your API keys, customer IDs, and raw usage events never persist on the hosting platform, keeping your financial data isolated.

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