Rate Limits

Last Updated: February 2026

BrewLogica enforces rate limits to ensure fair access for all users. Standard data operations (read/write brews and beans) have generous limits. AI-powered features like parse_brew_text and get_suggestions have separate monthly quotas.

API Rate Limits by Plan

Limit Type Free Plan Pro Plan
Requests per minute N/A (no MCP access) 60 req/min
Requests per day N/A 5,000 req/day
Concurrent connections N/A 5 simultaneous
Active API tokens 0 10 tokens
AI parse calls/month (parse_brew_text) N/A 200/month
AI suggestion calls/month (get_suggestions) N/A 100/month

MCP API access requires a Pro subscription ($49.99/year). Monthly AI quotas reset on the 1st of each calendar month.

How to Check Your Current Usage

Use the get_limits tool to check your current usage and remaining quota at any time. This tool requires no parameters.

Ask your AI assistant:

"How many AI requests do I have left this month?"

The assistant calls get_limits and returns a summary like: 

AI parse calls:    147 / 200 used this month (53 remaining)
AI suggestions:     61 / 100 used this month (39 remaining)
API requests today: 234 / 5000 used today
Rate limit:        60 req/min

Rate Limit Headers

Every API response includes standard rate limit headers so MCP clients can track usage programmatically:

Header Description
X-RateLimit-Limit Maximum requests allowed per minute
X-RateLimit-Remaining Requests remaining in the current minute window
X-RateLimit-Reset Unix timestamp when the current window resets
Retry-After Seconds to wait before retrying (only present on 429 responses)

What Happens When You Hit a Limit?

Per-minute limit exceeded (429 Too Many Requests)

The API returns a 429 status with a Retry-After header. Most MCP clients handle this automatically by waiting and retrying. Your AI assistant may pause briefly before continuing.

Daily limit exceeded

Standard data operations stop accepting new requests until midnight UTC. Read operations (list, get) continue at a reduced rate of 10 req/min.

Monthly AI quota exhausted

parse_brew_text and get_suggestions return an error indicating the quota is exhausted until the 1st of the next month. All other MCP tools continue working normally.

Tips to Stay Within Limits

  • Use batch prompts — "Log these 5 brews" works in one call rather than five separate requests
  • Use list_brews with filters before calling get_brew individually — fetch what you need in one request
  • Check get_limits at the start of long AI sessions to see your remaining AI quota
  • Revoke unused tokens from the tokens page — active tokens share the same rate limit pool