A Model Context Protocol (MCP) server for fetching historical currency exchange rates using the Frankfurter API.
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"currency-history-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# Currency History MCP A Model Context Protocol (MCP) server that provides historical currency exchange rates and currency conversion. Powered by the [Frankfurter API](https://api.frankfurter.app/), which is free and open-source. ## Features - **Get Historical Rates**: Fetch exchange rates for a specific date (e.g., "2023-01-01"). - **Convert Currency**: Convert amounts between currencies using historical rates. ## Installation & Usage (with uv) You can run this MCP server directly using `uv` without manually installing it everywhere: ```bash # Run directly uvx currency-history-mcp ``` Or install it as a tool: ```bash uv tool install currency-history-mcp ``` ## Manual Installation ```bash pip install currency-history-mcp ``` ## Running the Server ```bash # If installed via pip currency-history-mcp # Or connect via an MCP client inspector npx @modelcontextprotocol/inspector uvx currency-history-mcp ``` ## Tools 1. `get_historical_rate` - `date`: YYYY-MM-DD - `base`: Base currency (default USD) - `symbols`: Target currencies (default CNY, EUR, JPY, GBP) 2. `convert_historical_amount` - `amount`: Amount to convert - `from_curr`: Source currency - `to_curr`: Target currency - `date`: YYYY-MM-DD
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.