• SYNC
  • DATA
  • LOGS
  • HUMAN

How to report metered usage with your AI

Connect Stigg to your AI client to automate usage tracking. Once connected, your agent handles the data transmission for every event.

Ask AI about this page

Short answer

How can I report metered usage with my AI?

You tell your AI client to send usage events to Stigg. It maps your application's consumption data to your billing meters instantly. You'll see how the data flows in the breakdown below.

Usage data outcomes

Where your data lands

What happens when your AI processes usage events.

SYNC

Accurate billing

The AI sends consumption data to Stigg. Your usage-based plans stay in sync with real user activity.

DATA

Metered updates

Your agent pushes specific event counts or increments. This keeps your billing meters updated without manual exports.

LOGS

Usage visibility

The AI confirms that the data reached the right meter. You get a clear trail of what was reported and when.

HUMAN

Manual review

You decide if a usage spike looks suspicious. The AI reports the data, but you maintain control over billing disputes.

The workflow

What your AI does when usage occurs.

The AI acts as the bridge between your app logic and your billing engine.

  1. Identify usage

    Your agent detects when a user hits a specific feature or threshold in your application.

    gql_report_usage

  2. Send GraphQL updates

    The AI uses a GraphQL request to update specific meters in your Stigg dashboard.

    gql_report_usage

  3. Send REST updates

    If your setup prefers standard web requests, the AI sends the usage data via a REST call.

    rest_report_usage

  4. Verify transmission

    The AI checks the response from Stigg to ensure the usage event was accepted.

    rest_report_usage

Try it

Copy these to start.

Use these prompts to trigger usage reporting.

Starting points

Replace the bracketed text with your actual meter names or customer IDs.

Stigg Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_6N2TOJAyHFeDsPnzGGSq4Px2GqFliWpbYU9iV2r9/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Stigg capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "stigg-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_6N2TOJAyHFeDsPnzGGSq4Px2GqFliWpbYU9iV2r9/mcp"
    }
  }
}
Copy into chat04

  • Report 5 units of usage for customer 'cust_123' on the 'api_calls' meter.

  • Send a REST update to Stigg for the 'storage_gb' meter for user 'user_99'.

  • Use GraphQL to increment the 'active_seats' meter by 1 for account 'acc_456'.

  • Check if the usage report for the 'compute_hours' meter was successful.

  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Start here

Connect Stigg once, then ask.

One click connects your AI to Stigg. Your credentials stay encrypted and secure on our side.

Connect Stigg to your AI

FAQ

How this task behaves

  • 01

    Can the AI create new billing meters in Stigg?

    No. The AI can only report usage to existing meters using the provided tools.

  • 02

    Does the AI handle the actual credit card processing?

    No. The AI only reports the usage data that determines the amount to be charged.

  • 03

    Can I use both GraphQL and REST for reporting?

    Yes. You can instruct your AI to use either tool depending on your preference.

  • 04

    Will the AI delete my usage history?

    No. There are no tools available to delete or modify historical usage data.

  • 05

    How does the AI know which customer to bill?

    You must specify the customer or account identifier in your prompt when asking the AI to report usage.

  • More questions about Stigg? See everything the Stigg Connector can do

Connect Stigg to Claude, Cursor, ChatGPT & more