ai-rate-limit-tracker-api
Cloudflare Workers MCP server: ai-rate-limit-tracker. REST + MCP (JSON-RPC 2.0). Live: api.lazy-mac.com/ai-rate-limit-tracker
Catalog
io.github.lazymac2x/ai-rate-limit-tracker
Official4 toolsby lazymac2x
Cloudflare Workers MCP server: ai-rate-limit-tracker
Tracks and enforces rate limits for AI model API calls.
Captured live from the server via tools/list.
get_provider_limits
Get published rate limit specs (RPM, TPM, RPD, context window) for an AI provider and optional model.
Parameters (2)
- providerstringrequired
openai | anthropic | gemini | groq | cohere | mistral | together | deepseek
- modelstring
Model name (optional)
list_providers
List all AI providers supported by the tracker with their models and default limits.
No parameters.
track_usage
Record an AI API call and get real-time usage counters plus warnings if approaching limits.
Parameters (5)
- api_keystringrequired
Your tracker API key
- providerstringrequired
- modelstring
- tokens_usedinteger
- latency_msinteger
get_forecast
Forecast when rate limits will be exhausted and get scheduling recommendations.
Parameters (4)
- api_keystringrequired
- providerstringrequired
- modelstring
- rate_rpmnumber
Your actual request rate (requests/min)
Install
claude_desktop_config.json
{
"mcpServers": {
"ai-rate-limit-tracker": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://api.lazy-mac.com/ai-rate-limit-tracker/mcp"
]
}
}
}Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.