
Frankfurter MCP server
online · 100% uptimeio.github.lineofflight/frankfurter·v0.5.3·3 starsConvert currencies and fetch blended FX rates from 50+ institutional sources.
not scanned yet
3 stars
Reviews
Write oneNobody has reviewed Frankfurter yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Frankfurter tools
Tool list not cached yet. `describe` through the gateway fetches it live.
How Frankfurter compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 92/100
- higher than 95% of 48,255 servers
- Uptime
- 100%
- of our recent checks; the typical remote server answers 100%
- Response time
- 115 ms
- faster than 80% of 30,031 servers
- GitHub stars
- 3
- more than 80% of 28,688 servers
Release history: 3 versions in the registry since 2026-09-17, latest 2026-11-02, typically one every 36 days.
Install Frankfurter in Claude Code, Cursor or VS Code
claude mcp add --transport http frankfurter https://mcp.frankfurter.dev/
What the publisher says
From the Frankfurter repository's README, as published. We do not edit it. Read it on GitHub
frankfurter-mcp
Official Model Context Protocol server for the Frankfurter exchange-rate API. A thin, stateless proxy over Frankfurter's v2 blended multi-source reference rates.
Tools
returns a money object { amount, currency } rounded to the target's minor units. Pass date for a historical rate, provider for one institution's published rate (e.g. UST, the U.S. Treasury's quarterly reporting rate).
- convert — the primary tool. Convert an amount between two currencies;
date. Optional base, quotes and provider. The raw-rate companion to convert; with provider and the provider's own base, the digits are as published, with the date they took effect.
- getrates** — blended reference rates for the latest day or a single
frequency and coverage dates, to pick a provider.
- listcurrencies** — supported ISO 4217 codes and names as { code: name }.
- listproviders** — the institutions relayed, with key, rate type,
For time series, historical ranges, or bulk queries, use the REST API at https://api.frankfurter.dev/v2 directly.
Rates are daily reference rates, not real-time trading rates. Not financial advice.
Run
npm install
npm run build
npm start # listens on :3000, POST /Docker:
docker build -t frankfurter-mcp . && docker run -p 3000:3000 frankfurter-mcp
docker run -p 3000:3000 ghcr.io/lineofflight/frankfurter-mcp:latestThe prebuilt ghcr.io/lineofflight/frankfurter-mcp:latest image is published on each release; building from source also works.
Point any MCP client at http://:3000/ (Streamable HTTP). The hosted server is at https://mcp.frankfurter.dev/.
Configuration
Set this to a self-hosted Frankfurter instance if desired. The value must be a host root: any path prefix in it is discarded (e.g. https://example.com/api resolves to https://example.com/v2/rates), so a self-hosted instance must be reachable at the host root.
- PORT — HTTP port (default 3000).
- FRANKFURTERAPIURL — upstream API base (default https://api.frankfurter.dev).
Development
npm test # vitest
npm run lint # biomeLicense
MIT
Nothing above is checked by us. What we check is on the safety report.
Grade history
- 2026-09-19restoreC → Ascore 92
Frankfurter: common questions
- Is Frankfurter MCP server safe?
- Yes, by our scan: it is graded A (92/100). Read the Frankfurter safety report
- How do I install Frankfurter?
- It runs remotely at mcp.frankfurter.dev. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
- Does Frankfurter need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Frankfurter maintained?
- The last commit was 42 days ago (2026-09-23). The latest release is v0.5.3.
- Is Frankfurter up?
- 100% of our last 28 checks got an answer. We check remote servers about four times a day.
- How does Frankfurter compare with other MCP servers?
- safety score 92/100 (higher than 95% of 48,255 servers); uptime 100% (of our recent checks; the typical remote server answers 100%); response time 115 ms (faster than 80% of 30,031 servers). Full comparison.