Historical Exchange Rate Retrieval With Lru Caching

** - MCP server acting as an interface to the [Frankfurter API](https://frankfurter.dev/) for currency exchange data.

Unique: Implements LRU caching specifically for historical queries (separate from TTL cache for latest rates), recognizing that historical data is immutable and benefits from long-term caching. 1024-item capacity balances memory usage against typical agent workflows that may query 10-50 distinct historical periods.

vs others: More efficient than calling Frankfurter API repeatedly for the same historical dates; LRU strategy is appropriate for historical data (unlike TTL, which assumes data freshness matters) and avoids unbounded memory growth

via “retrieve historical exchange rates”

Currency conversion and exchange rates for AI assistants. 170+ currencies (fiat + major crypto), historical data back to 1999, free tier, MIT-licensed. **Tools:** - `convert` — convert an amount between currencies at the latest rate - `latest_rate` — current rate (single pair) or full table for a b

Unique: Access to a comprehensive historical database dating back to 1999, allowing for detailed financial analysis.

vs others: More extensive historical data range compared to many alternatives, which often limit access to recent years.