Integration
Route Cursor through RemKey
Cursor is the AI code editor. Here's the one change that puts it behind a governed gateway.
Cursor lets you override the OpenAI base URL and supply your own key. That override is all RemKey needs. Once set, autocomplete, chat, and Composer traffic flows through RemKey, routed to the right tier, screened for secrets, and logged.
Why route it through RemKey
- Stop leaking secrets into model context. RemKey's PII/API-key detector screens every completion request fail-closed, so an API key sitting in an open buffer never rides along to a provider.
- Classifier routing trims spend on the constant stream of small edits and completions Cursor generates, cheap edits get a cheap tier automatically.
- One revocable key per developer. Rotate or kill a Cursor key instantly from the RemKey dashboard without touching your provider account.
- A signed, hash-chained audit trail of exactly what your editor sent to which model, the record a CISO can verify offline.
Swap these lines
Cursor → Settings → Models → OpenAI API Key → Override Base URL
# Cursor: Settings (Cmd/Ctrl+Shift+J) → Models # 1. Turn on "Override OpenAI Base URL" # 2. Paste the RemKey base URL and key below Base URL: https://remkey.ai/v1 API Key: rk_live_...your RemKey key... # Click "Verify", Cursor pings /v1/models through RemKey. # Keep gpt-4o / your model of choice enabled; RemKey routes the tier.
Cursor sends both Authorization: Bearer and, for some paths, custom auth, RemKey accepts Bearer and x-api-key, so verification just works.
Drop-in by design. RemKey accepts both Authorization: Bearer and x-api-key, and serves the native OpenAI and Anthropic wire formats. The base-URL swap is the only code change.