How to Use the Lago MCP in Windsurf

Q: How do I check a customer's invoice history?

Ask your agent to get the data. It will use the getcustomer tool to find the right account and then listinvoices to pull their entire invoice history for you to review.

Let Windsurf's Cascade agent manage your Lago billing, from creating plans to sending usage events, all in one autonomous run.

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 Windsurf

Create your Vinkius account to connect Lago to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Onboard Customers Autonomously

This MCP Server lets Windsurf's Cascade agent handle your entire customer onboarding process in Lago. Give it a high-level goal like "Onboard New Client Corp with the Pro plan." Cascade chains the tools together, running `upsert_customer` to create the record, then `create_subscription` to assign the plan, all without you prompting each step. It's a completely different way of working. Instead of you manually calling one tool after another, you define the end state. Cascade figures out the sequence, even using `create_wallet` if the plan requires prepaid credits. You get a fully provisioned customer in Lago from a single instruction.

Manage Metered Billing with this MCP Server

Set up and manage complex usage-based pricing models directly from your IDE. Ask Windsurf to define a new billable item, and its Cascade agent will use `create_billable_metric` to register it in Lago. Then, tell it to build a new pricing tier, and it will run `create_plan` to attach a price to that metric. Once your plans are live, your application can feed usage data right back to Windsurf. It knows when to use `send_event` for real-time updates or `batch_events` to efficiently report high-volume activity. Your agent handles the logic of logging every billable action for you.

Automate Coupon and Invoice Checks

Run billing-related admin tasks without ever opening a web dashboard. You can instruct Windsurf to "Apply a 10% launch discount to our first 20 customers." Cascade will get the customer list, use `create_coupon` to generate the discount, and then `apply_coupon` to each subscription in sequence. This also works for routine checks and reporting. Set up a recurring task for Cascade to `list_invoices` for a specific period or to `get_subscription` to confirm a customer's active status. Windsurf gets the data from Lago and presents it right in your editor, making financial oversight part of your development workflow.

Setup guide

Set up Lago MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the Lago MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Lago payment history." If connected, Cascade will call the Lago tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "lago-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Windsurf

Windsurf's Cascade agent chains commands. You state the goal, and it automatically calls `upsert_customer` and then `create_subscription` in the correct sequence to get a customer subscribed to a plan in Lago.

Yes. You can instruct Windsurf to collect usage data and send it to Lago. The agent is smart enough to use the `batch_events` tool for efficiency when dealing with large volumes of events.

Just tell Windsurf what you need. For example, "Create a new 'Enterprise' plan that meters API calls." The Cascade agent will use the `create_billable_metric` and `create_plan` tools to set it all up in your Lago account.

Ask your agent to get the data. It will use the `get_customer` tool to find the right account and then `list_invoices` to pull their entire invoice history for you to review.

The server processes customer external IDs, subscription details, plan codes, and usage event data. Vinkius secures the connection by running each request in an ephemeral, zero-trust V8 Isolate sandbox, authenticated with a short-lived token.

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