Key Health Monitoring
Clevername automatically validates your stored API keys every 6 hours. If a key is invalid, expired, or rate-limited, it is flagged on your dashboard so you can take action before it disrupts your agents.
What is key health monitoring?
Key health monitoring is an automatic background check that verifies your stored API keys are still valid and functional. Every 6 hours, Clevername makes a lightweight validation call to each provider to confirm the key works. If a key fails validation, it is flagged on your dashboard.
What gets checked
The health check verifies:
- Authentication — does the provider accept the key?
- Permissions — does the key have the expected scopes?
- Rate limits — is the key currently rate-limited or throttled?
- Account status — is the provider account active and in good standing?
Health statuses
Key is valid and working normally.
Key works but is rate-limited or has reduced permissions.
Key is rejected by the provider. Needs replacement.
Automatic check runs
Every 6 hours, the health check runs in the background. It makes a minimal API call to each provider (typically a models list endpoint) to verify the key is accepted. This call does not consume meaningful quota or generate costs.
Key is flagged
If the provider rejects the key (401/403 response), the key's health status is set to Invalid. If the key is rate-limited (429 response), it is marked as Degraded. The status and last-checked timestamp are stored alongside the key metadata.
Dashboard shows the issue
Invalid and degraded keys appear with a warning badge on the API Keys settings page and on any agent that has the key bound. You also receive a notification if you have key health alerts enabled in your notification preferences.
You take action
For Invalid keys, you need to replace the key — either by pasting a new one (which triggers interception) or by updating it from the API Keys settings page. For Degraded keys, the issue is usually temporary and resolves on the next check.
On-Demand Health Check
You do not have to wait for the scheduled check. You can trigger a health check at any time:
From the dashboard
Go to Dashboard → Settings → API Keys. Click the Check Health button next to any key. The result updates within a few seconds.
From MCP tools
Use the key_health_check MCP tool to validate a specific key or all keys at once. This is useful for automation workflows that need to verify keys are healthy before starting a batch job.
What Health Monitoring Does Not Do
Health monitoring is a validation tool, not an enforcement tool. It is important to understand the boundaries:
| It does | It does not |
|---|---|
| Flag invalid keys on the dashboard | Automatically disable agents using invalid keys |
| Send notifications when keys fail | Rotate keys automatically |
| Track health history over time | Delete or replace keys without your action |
| Verify provider account status | Check billing balances or credit limits |