Supercharge your AI with Unit & FX Calculator. Stop Math Hallucination. Get Deterministic Conversions.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Connect to your AI in seconds.
Unit & FX Calculator provides deterministic math for unit conversion and real-time currency rates. Stop LLMs from guessing exchange rates or mixing metric/imperial units.
This server uses exact mathematical engines to convert length, mass, volume, temperature, and speed; it also pulls live rates directly from the European Central Bank.
What your AI can do
Batch convert
Converts multiple physical units (like volume or temperature) in one deterministic pass for quick batch processing.
Convert unit
Deterministically converts a single physical unit, such as converting kilometers per hour to miles per hour using precise math logic.
Get rate
Retrieves the current foreign exchange rate between two currencies using the European Central Bank data source with an hourly local cache.
You give it a value and two units (e.g., Celsius to Fahrenheit), and the tool returns the mathematically precise equivalent.
The system accepts an array of values and converts them all at once using one deterministic calculation pass.
You specify two three-letter currency codes (e.g., USD to JPY), and the tool returns the current, precise market rate from the European Central Bank.
Ask an AI about this
Compatible AI Apps
OAuth 2.0 Compatible Gemini Waiting for input…
Unit & FX Calculator MCP Server: 3 Tools for Math Accuracy
Access three specialized tools that guarantee accurate physical unit conversions and real-time financial data retrieval, eliminating math hallucination.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Unit & FX Calculator on VinkiusBatch Convert
Converts multiple physical units (like volume or temperature) in one deterministic pass for quick batch processing.
Convert Unit
Deterministically converts a single physical unit, such as converting kilometers per...
Get Rate
Retrieves the current foreign exchange rate between two currencies using the...
Connect to your AI in seconds. Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Claude AI
Open Claude Settings
Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
Add Custom Connector
Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:
https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp
Replace [YOUR_TOKEN_HERE] with your token from
cloud.vinkius.com. For OAuth-protected servers, expand Advanced
settings to add credentials.
Start a conversation
Open a new chat. The Unit & FX Calculator integration is available immediately — no restart needed.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Unit & FX Calculator, then connect any of our 5,000+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,000+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Math.js & Frankfurter. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This connection provides 3 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Unit Conversion Shouldn't Require Manual Lookups or Math Sheets.
Right now, if you need to convert a measurement like 120 km/h to mph, you either have to trust an LLM—which might round it incorrectly—or leave the chat and open a separate calculator. If you're working with mixed units (like volume or temperature), that manual process gets worse fast; you're copy-pasting values across three different tabs just to ensure your math is right.
With this MCP, you call `convert_unit` directly within the chat flow. You feed it the source and target unit, and the agent returns a single, perfectly rounded number backed by an exact mathematical engine. It's that simple.
The Unit & FX Calculator MCP Server: Get Live Rates and Batch Conversions.
Before this server, running a large financial model meant making sure every currency rate was pulled manually or relying on cached data that might be hours old. If you ran 50 conversions in a row, the risk of hitting an API limit or using stale rates was high.
Now, use `get_rate` to fetch live European Central Bank feeds for your required currencies. Plus, if you've got a huge list of values to check, `batch_convert` handles it all deterministically in one shot.
What your AI can actually do with this
Listen up, because when your AI client needs math that's actually right—not some educated guess—you don't trust a standard LLM. Those things are notorious for messing up conversions, whether it's mixing metric and imperial units or hallucinating exchange rates based on data from last year. This server fixes that. It hooks your agent into a dedicated mathematical engine and a live financial feed, giving you the numbers you need, period.
When you use this toolset, you get deterministic math for every physical conversion imaginable: length, mass, volume, temperature, and speed. You'll never have to worry about approximation again.
If you just gotta convert one thing—say, taking a value like 65 miles per hour and turning it into kilometers per hour—you call convert_unit. It uses precise math logic that guarantees the correct equivalent every single time. You give it a starting value and two units, and it spits out the mathematically exact answer.
That's how you get reliable unit conversions.
But what if you got a spreadsheet full of numbers? Maybe you gotta convert a dozen different volumes or temperatures all at once. Don't run twelve separate calls; just hit batch_convert. This tool accepts an array of values and processes them in one deterministic pass, making quick batch processing painless.
It handles the whole bulk conversion for you.
When it comes to money, forget those historical rates your agent might pull from its training data. For real currency exchange, you'll use get_rate. You tell it two three-letter currency codes—like USD and JPY—and it pulls the current market rate directly from the European Central Bank. This isn't old info; it's what the global market is using right now.
We built this whole system to avoid guesswork. The math engines handle conversions for things like Celsius to Fahrenheit or kilometers per hour to miles per hour with surgical precision. And when you need a rate, get_rate uses an hourly local cache on the European Central Bank data source, so if you're running massive conversion jobs, it doesn't bog down or hit rate limits.
Here’s how it plays out: You tell your agent to calculate something complex. It recognizes that it needs a reliable math toolset and executes the steps automatically. Whether you need convert_unit for a single measurement, batch_convert for twenty measurements, or get_rate because you're dealing with foreign currency, the results are always mathematically solid.
It’s about getting accurate data when your workflow depends on it. You'll stop spending time verifying if that number is right and start using the numbers to get work done.
019e3901-d462-7389-85e4-1676d19edc82 
Here's how it actually works
The bottom line is: you stop relying on general LLM knowledge for math that needs to be perfectly accurate right now.
Tell your agent exactly what you need: a conversion or an exchange rate.
The server executes the appropriate tool (convert_unit, batch_convert, or get_rate) using its external math and finance APIs.
You get back a deterministic, precise answer—either the converted number or the live market rate.
Who is this actually for?
Financial analysts who build models and need real-time rate checks. Data scientists running simulations involving mixed units (like speed or volume). Engineers dealing with international standards where precise measurement is critical. Anyone whose work depends on math that can't hallucinate.
Uses get_rate to check currency fluctuations before running a batch of financial calculations, ensuring the numbers are based on today’s market.
Runs convert_unit to accurately switch between imperial and metric measurements (like converting miles per hour to kilometers per hour) for project documentation.
Uses batch_convert when processing a large dataset of temperatures or volumes, needing to convert all values simultaneously without losing float precision.
What Changes When You Connect
Eliminate math errors when converting units. Instead of risking an LLM guessing the conversion factor, use convert_unit for guaranteed accuracy on single values (e.g., Fahrenheit to Celsius).
Handle large datasets instantly. If you have a list of 100 volumes or speeds to check, run them through batch_convert. It processes everything deterministically in one go.
Use today's actual currency rates. Don't rely on outdated training data for finance. Call get_rate to pull live FX feeds from the European Central Bank.
Save time with local caching. Because we cache FX rates locally for an hour, running repetitive batch conversions is fast and won't hit external rate limits.
Support complex units. This tool handles more than just length; it deals with speed (km/h to mph) and temperature, making it useful across engineering domains.
See it in action
Standardizing international project specs
A civil engineer needs to update a spec sheet that mixes metric measurements for volume and imperial measurements for length. Instead of manually checking the conversion factors, they ask their agent to run convert_unit multiple times until all units match the target standard (e.g., converting cubic meters to gallons). The process is guaranteed accurate.
Validating a multi-currency investment portfolio
A financial analyst needs to check the current conversion value of several holdings across different currencies (USD, EUR, GBP). They run get_rate for each pair. The agent pulls the live rates from the ECB and gives them a consolidated report, preventing old data errors.
Processing sensor data logs in bulk
A scientist collects 50 temperature readings over an hour, some recorded in Celsius and others in Kelvin. Rather than running 50 individual conversions, they use batch_convert to process the entire list instantly with guaranteed float precision.
Calculating speed differences across borders
A logistics manager is comparing vehicle speeds recorded from different regions—some in km/h and some in mph. They instruct their agent to use convert_unit to standardize every single entry into a consistent unit (e.g., always report in MPH).
The honest tradeoffs
Relying on general knowledge
Asking an LLM, 'What's 100 km/h in mph?' and getting a slightly rounded answer that might be off by a fraction.
Always use the convert_unit tool. This forces the agent to run the calculation through the deterministic math engine, ensuring the specific decimal rounding you need.
Handling multiple currency pairs
Manually querying exchange rates for USD/CAD, EUR/JPY, and GBP/AUD over several days.
Use get_rate. It pulls the live rate from a central source (the ECB) and caches it locally, so you don't waste time on repetitive checks.
Converting large arrays of data
Trying to process 20 different batch conversions by making 20 separate API calls.
Don't call the tool multiple times. Use batch_convert once, passing all values and units in a single request for maximum efficiency.
When It Fits, When It Doesn't
Use this server if your task involves measurable conversions—currency exchange, physical units, or batch processing of those numbers. You need the math to be deterministic; you can't afford rounding errors or hallucinated rates.
Don't use it if you just need general information (e.g., 'What is a kilometer?'). Use this server only when the output must pass rigorous mathematical or financial validation. If you only need to know how to convert units, that’s fine for general knowledge; but if you need the actual converted number, use convert_unit.
If your job involves comparing multiple different currency pairs over a single session, always opt for get_rate. Never try to calculate rates yourself—let the API handle it.
Questions you might have
How do I use the batch_convert tool? +
You pass an array containing the value, source unit, and target unit to batch_convert. It handles multiple conversions at once in a single deterministic pass.
Is the currency rate from get_rate always up-to-date? +
Yes. The tool pulls rates directly from the European Central Bank (Frankfurter API). Plus, it caches these rates locally for one hour, making subsequent calls fast.
Can convert_unit handle complex units like speed? +
Yep. convert_unit is built to handle multiple physical dimensions, so you can accurately switch between speed units (like km/h and mph) or temperature scales.
What if I run get_rate repeatedly in a short time? +
You won't. The tool caches the rate locally for one hour, so repeated calls within that window are instant and don't stress external APIs.
How long is the cache duration when using get_rate? +
The exchange rate data is cached for one hour. This means if you run multiple conversions within that window, subsequent calls are instantaneous and won't trigger rate limits, which speeds up large batch jobs.
What happens when convert_unit receives bad input? +
The tool validates all inputs against known units. If you give it a non-standard unit or an invalid format, the engine throws a specific error message telling you exactly what needs correcting.
What data types can batch_convert process efficiently? +
It accepts arrays containing values, source units, and target units. The underlying mathematical model processes standard numeric inputs across all dimensions reliably.
Is the data from get_rate secure and traceable to me? +
No, the rates come directly from the European Central Bank. We only fetch public reference rates; your specific conversion history is managed by your AI client's session, not stored on our end.
How often are currency rates updated? +
Rates are fetched live and cached for exactly 1 hour.
What physical units are supported? +
Length, mass, volume, temperature, and speed are fully supported via mathjs.
Can it batch convert an array of data? +
Yes, the batch processor can handle large JSON arrays instantly.
We've already built the connector for Unit & FX Calculator. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 3 tools are live and waiting.
You're up and running in seconds.
Gemini Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.