---
title: "Rate limits"
description: "Per-key rate limits on the SHINE AI MCP server. Two tiers, enforced per minute and per day."
---

> Documentation Index
> Fetch the complete documentation index at: https://docs.shineai.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Rate limits

Every key — OAuth-issued or dashboard-created — carries two rate limits: per minute and per day. Limits are enforced at the Worker edge.

## Tiers

| Tier | Per minute | Per day |
|---|---|---|
| Limited | 60 | 10,000 |
| Pro | 300 | 100,000 |

Dashboard-created keys default to Pro. OAuth-issued keys default to Limited.

## Response headers

Every response to `/v1/mcp` carries:

```
X-RateLimit-Limit-Minute: 300
X-RateLimit-Remaining-Minute: 287
X-RateLimit-Limit-Day: 100000
X-RateLimit-Remaining-Day: 94812
```

## Over the limit

Returns HTTP 429 with:

```json
{ "error": "rate limit exceeded", "retryAfterSec": 42 }
```

The `Retry-After` header is also set. AI apps surface this as a transient error and retry after the window.

Source: https://docs.shineai.io/mcp/rate-limits/index.mdx