Sources
Where Opusgen sees agents. Each source is a few lines in front of something Postbox already runs.
Connected
| Source | Installed as | Requests, 30 days | Last request | Status |
|---|---|---|---|---|
| Docs/docs, /llms.txt, /pricing | Next.js proxy | 186,721 | 15 s ago | Healthy |
| API/v1/* | Cloudflare Worker | 94,891 | just now | Healthy |
| MCP serversend_email, create_domain, list_templates | @opusgen/mcp | 18,366 | just now | Healthy |
| Signup and billing/signup, /v1/accounts, billing webhooks | Webhook | 6,122 | 31 s ago | Healthy |
InstallThe edge snippet, as Postbox installed it
// proxy.ts
import { opusgen } from "@opusgen/next";
export default opusgen({ key: process.env.OPUSGEN_KEY });What we see, and what we never see
We see
- Requests to your docs, API, MCP server and signup
- Which agent sent each one, and how sure we are
- The account and billing events you connect
We never see
- Prompts, or the conversation between a person and their agent
- PII. It is redacted at ingest, and you control retention
Agent identification
0.80
Requests below this count as an unidentified agent.
AlertsSent to the team's alerts channel and by email
Last alert
Model releaseOct 1, 06:12
codex vNext: efficacy −12 pts on /v1/send