FrankfurterMCP
About
MCP server acting as an interface to the [Frankfurter API](https://frankfurter.dev/) for currency exchange data.
Details
- Author
- anirbanbasu
- Categories
- Database, Community, Other
Jump to
Setup
Install FrankfurterMCP in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/anirbanbasu/frankfurtermcp
Follow the installation instructions in the repository README, then restart your MCP client.
If your objective is to use the tools available on this MCP server, please refer to the usage > client sub-section below.
The directory where you clone this repository will be referred to as theworking directoryorWDhereinafter.
Following is a list of environment variables that can be used to configure the application. A template of environment variables is provided in the file.env.template.Note that the default values listed in the table below are not always the same as those in the.env.templatefile.
The following environment variables can be specified, prefixed withFASTMCP_:HOST,PORT,DEBUGandLOG_LEVEL.
The underlying HTTP client also respects some environment variables, as documented inthe HTTPX library. In addition,SSL_CERT_FILEandSSL_CERT_DIRcan be configured to use self-signed certificates of hosted API endpoint or intermediate HTTP(S) proxy server(s).
Frankfurter MCP will cache calls to the Frankfurter API to improve performance. The cache happens with two different strategies. For API calls whose responses do not change for certain parameters, e.g., historical rate lookup, a least recently used (LRU) cache is used. For API calls whose responses do change, e.g., latest rate lookup, a time-to-live (TTL) cache is used with a default time-to-live set to 15 minutes. The cache parameters can be adjusted using the environment variables, see below.
The following sub-sections illustrate how to run the Frankfurter MCP as a server and how to access it from MCP clients.
While running the server, you have the choice to usestdiotransport or HTTP options (sseor the newerstreamable-http).
Using default settings andMCP_SERVER_TRANSPORTset tosseorstreamable-http, the MCP endpoint will be available over HTTP athttp://localhost:8000/ssefor the Server Sent Events (SSE) transport, orhttp://localhost:8000/mcpfor the streamable HTTP transport.
If you want to run Frankfurter MCP withstdiotransport and the default parameters, execute the commands below without using the.env.templatefile.
Optional: Copy the.env.templatefile to a.envfile in theWD, to modify the aforementioned environment variables, if you want to use anything other than the default settings. Or, on your shell, you can export the environment variables that you wish to modify.
Run the following in theWDto start the MCP server.
Add this package from PyPI usingpipin a virtual environment (possibly managed byuv,pyenvorconda) and then start the server by running the following.
Optional: Add a.envfile with the contents of the.env.templatefile if you wish to modify the default values of the aforementioned environment variables. Or, on your shell, you can export the environment variables that you wish to modify.
pip install frankfurtermcp python -m frankfurtermcp.server
There is a Dockerfile provided in this repository,local.dockerfile, for containerising the Frankfurter MCP server. First, make a copy of the.env.templateto a.envfile. Then, modify the following variables in the.envfile as needed.
- FASTMCP_HOST: Set to0.0.0.0to allow external access to the container.This is only for local testing and is not recommended for production deployments.
- CORS_MIDDLEWARE_ALLOW_ORIGINS: Set toto allow external access to the MCP server from any origin.This is needed if you want to test the server using the MCP Inspector over HTTP transport and is not recommended for production deployments.
To build the image, create the container and start it using Docker Compose, run the following inWD.
If you change the port to anything other than 8000 in.env,do remember to change the port number indocker-compose.yml.
Note: The minimum Docker Compose version needed is 2.24.0. You can check your version by runningdocker compose version. If you have an older version, please update Docker Desktop to get the latest Docker Compose. In addition, the backend must be BuildKit capable.
To run in detached mode (background), add the-dflag:
To run the container and use the local Frankfurter API server, run the following command. Attach the-dflag to run in detached mode. Check thelocal_api.env.templatefile to specify the optional environment variables used by the local API server.
Note: Upon starting the first time, the local Frankfurter API may need some time to fetch updated exchange rates. For subsequent runs, the local Frankfurter API will use cached data and should be faster to start although it will still fetch the latest rates.
FRANKFURTER_API_URL=http://frankfurter_api:8080/v1 docker compose --profile local_api up --build frankfurtermcp frankfurter_api
To stop the container group created with thelocal_apiprofile, run the following command.
Thedocker-compose.ymlfile includes security hardening with read-only filesystem (where relevant), dropped capabilities and resource limits.
Note: The local API server is built using the latest code from theFrankfurter GitHub repository, hence this may be unstable. If you want to use a specific commit, change thecontextfield forbuildunderfrankfurter_api_basein thedocker-compose.ymlfile to point to the specific commit hash, e.g.,https://github.com/lineofflight/frankfurter.git#0b6dbd80716f5abe27e8759fc548b74d35fa82b9to use commit0b6dbd80716f5abe27e8759fc548b74d35fa82b9.
Upon successful build and container start, the MCP server will be available over HTTP athttp://localhost:8000/ssefor the Server Sent Events (SSE) transport, orhttp://localhost:8000/mcpfor the streamable HTTP transport. If you are also starting the local Frankfurter API server, the API endpoint will be available athttp://localhost:8080/v1.
The currently available cloud hosted options are as follows.
- FastMCP Cloud:https://frankfurtermcp.fastmcp.app/mcp
- Glama.AI:https://glama.ai/mcp/servers/@anirbanbasu/frankfurtermcp
This sub-section explains ways for a client to connect and test the FrankfurterMCP server.
To use it, you must have Node.js installed. The best way to install and managenodeas well as packages such as the MCP Inspector is to use theNode Version Manager (or,nvm). Once you havenvminstalled, you can install and use the latest Long Term Release version ofnodeby executing the following.
Following that (install and) run the MCP Inspector by executing the following in theWD.
npx @modelcontextprotocol/inspector uv run frankfurtermcp
This will create a local URL at port 6274 with an authentication token, which you can copy and browse to on your browser. Once on the MCP Inspector UI, pressConnectto connect to the MCP server. Thereafter, you can explore the tools available on the server.
Claude Desktop, Visual Studio, and so on
The server entry to run withstdiotransport that you can use with systems such as Claude Desktop, Visual Studio Code, and so on is as follows.
{ "command": "uv", "args": [ "run", "frankfurtermcp" ] }
{ "command": "uvx", "args": [ "frankfurtermcp" ] }
Instead of havingfrankfurtermcpas the last item in the list ofargs, you may need to specify the full path to the script, e.g.,WD/.venv/bin/frankfurtermcp. Likewise, instead of usinguv, you could also have the following JSON configuration with the path properly substituted forpython3.12, for instance such asWD/.venv/bin/python3.12.
{ "command": "python3.12", "args": [ "-m", "frankfurtermcp.server" ] }
FrankfurterMCP has the following MCP features.
The following table lists the names of the tools as exposed by the FrankfurterMCP server. The descriptions shown here are for documentation purposes, which may differ from the actual descriptions exposed over the model context protocol.
The required and optional arguments for each tool are not listed in the following table for brevity but are available to the MCP client over the protocol.
Installprek. Then enableprekby running the following in theWD*.
Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
To run the provided test cases, execute the following. Add the flag--capture=tee-systo the command to display further console output.
Invokejust test-coverageto run all the tests and generate a coverage report as follows. If all tests are run, the generated coverage report may look like the one below.
---------------------------------------------------------------------------------------- benchmark: 2 tests --------------------------------------------------------------------------------------- Name (time in ms) Min Max Mean StdDev Median IQR Outliers OPS Rounds Iterations --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- test_get_historical_exchange_rates 4.4944 (1.0) 5.1512 (1.0) 4.7919 (1.0) 0.2460 (1.0) 4.7819 (1.0) 0.3249 (1.0) 2;0 208.6840 (1.0) 5 1 test_get_latest_exchange_rates 4.7937 (1.07) 5.6976 (1.11) 5.3257 (1.11) 0.3345 (1.36) 5.4182 (1.13) 0.3575 (1.10) 2;0 187.7702 (0.90) 5 1 --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- Legend: Outliers: 1 Standard Deviation from Mean; 1.5 IQR (InterQuartile Range) from 1st Quartile and 3rd Quartile. OPS: Operations Per Second, computed as 1 / Mean =============================================================== 15 passed in 4.09s =============================================================== Name Stmts Miss Cover Missing --------------------------------------- TOTAL 265 0 100.00% 6 files skipped due to complete coverage. Test coverage complete.
This section documents security-related findings from vulnerability scans and provides context for deployment decisions.
Airtable vulnerability scan findings and rationale
Check for security-related findings fromthe Airtable vulnerability scan(search forfrankfurtermcp) below, along with rationale and counter-arguments.
The current status of the project isactiveas of the last update of this README. See theCHANGELOGfor a detailed list of changes.
Read and write access to Airtable databases.
BigQuery database integration with schema inspection and query capabilities
Server implementation for Google BigQuery integration that enables direct BigQuery database access and querying capabilities
A MCP server that provides real-time cryptocurrency market data through CoinCap's public API without requiring authentication
Universal database MCP server supporting multiple database types including PostgreSQL, Redshift, CockroachDB, MySQL, RDS MySQL, Microsoft SQL Server, BigQuery, Oracle DB, and SQLite
MCP server for autonomous data exploration on .csv-based datasets, providing intelligent insights with minimal effort.
Universal database MCP server supporting mainstream databases.
MCP server for dbt-core (OSS) users as the official dbt MCP only supports dbt Cloud. Supports project metadata, model and column-level lineage and dbt documentation.
Leverages your Schemas and Access Patterns to interact with your DynamoDB Database using natural language.
MCP server for libSQL databases with comprehensive security and management tools. Supports file, local HTTP, and remote Turso databases with connection pooling, transaction support, and 6 specialized database tools.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
