Agent Metering

Last 30 days

Uptime

100%

Response time

163 ms typical, 163 ms slowest 5%

Last check

6 h ago

Next check

any minute now

How to call it

Add it to any MCP client that supports remote servers.

{
  "mcpServers": {
    "agent-metering": {
      "type": "http",
      "url": "https://mcp.viridisconservation.com/metering/mcp"
    }
  }
}

11 tools

• create_meter

  Create a usage meter between a provider and a consumer agent. unit: what is being counted (call, token, kwh, ...). Price is in minor currency units (cents) per unit. Returns the meter_id.

• record_usage

  Record a usage event. Idempotent on event_id (safe to retry — never double-billed). outcome is 'ok' or 'error' and feeds the SLA report.

• usage_summary

  Totals for a meter: event count, total quantity, accrued minor units.

• sla_report

  Pure SLA report: success_rate vs sla_target, breach flag. No mutation.

• close_period

  Freeze all open events into an immutable invoice (exactly-once). The invoice amount is what agent-escrow-agent should settle.

• verify_chain

  Verify the tamper-evident event hash chain for a meter.

• list_meters

  List all meters with event/invoice counts.

• list_events

  Read usage events (paginated, read-only). Filter by meter, provider, consumer_class (internal|external|unknown), channel, outcome (ok|error), and ISO date range [since, until). Test-flagged events are excluded unless include_test=true. Returns events + next_cursor.

• usage_timeseries

  Usage time series bucketed on each event's recorded_at (UTC; bucket=day|hour), grouped across meters by provider — a real time-series primitive, independent of meter creation times. Includes per-bucket breakdowns by consumer_class / channel / provider. est_accrued_min

• flag_meter

  Admin: flag/unflag a meter as test/synthetic so its events are excluded from usage statistics by default. Touches meter metadata only — never events, never the hash chain, never billing accruals. Requires the server's VIRIDIS_ADMIN_TOKEN.

• describe_agent

  Fleet-standard self-description.

Security scan

• No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks