Overview
Interest Rate works by aggregating central bank policy rate data from FRED (Federal Reserve Economic Data) for 22 major central banks including the Federal Reserve, European Central Bank, Bank of England, and more. Data is refreshed daily with historical data available back to 2000.
Live Test Interest Rate Grounding Data Source →
The tool
Once your client is connected to the VerveContext server, this appears in its tool list as InterestRateGroundingData. It is read-only and open-world — it fetches and never mutates anything on your side — so most clients call it without asking you to confirm.
{
"name": "InterestRateGroundingData",
"arguments": {
"country": "US"
}
}You do not name the tool yourself; the model picks it. Asking about US in the terms this source covers is enough for it to reach for InterestRateGroundingData on its own — naming it explicitly also works, and is the way to force the call.
Connecting
One server URL covers every source in the catalog, including this one. Authorization is OAuth: the client opens a browser once, and there is no key to paste into a config file.
{
"mcpServers": {
"vervecontext": {
"url": "https://api.vervecontext.com/v1/mcp"
}
}
}https://api.vervecontext.com/v1/mcpPer-client setup — Claude, Cursor, VS Code, ChatGPT — is on the MCP setup page.
Arguments
These are the properties on the tool's inputSchema, so a well-behaved client validates them before the call is made. Premium arguments are accepted on every plan but only take effect on plans that include them.
| Argument | Type | Description |
|---|---|---|
countryRequired | string | 2-letter country codeAUBRCACHCNCZDKEU+14length 2–2 |
dateOptionalPremium | string | Optional month in YYYY-MM format for a historical lookup. Omit for the current rate. |
What the model gets back
The result carries a structuredContent object matching the tool's declared outputSchema, so a client reads fields without parsing prose. status is "ok" and error is null on success; a null field means the value was not available for that input, not that the call failed.
{
"status": "ok",
"error": null,
"data": {
"country": "US",
"countryName": "United States",
"centralBank": "Federal Reserve",
"rate": 4.5,
"date": "2026-02-05",
"lastUpdated": "2026-02-05T05:00:00.000Z",
"lastChanged": "2026-01-29",
"change": -0.25,
"changeDirection": "down",
"previousRate": 4.75
}
}
Response fields
Paths are relative to data. Premium fields are absent rather than zeroed on plans that do not include them, so check for presence instead of comparing to 0.
| Field | Type | Example | Description |
|---|---|---|---|
country | string | US | Two-letter ISO country code for the nation |
countryName | string | United States | Full name of the country in English |
centralBank | string | Federal Reserve | Name of the central bank managing monetary policy |
rate | number | 4.5 | Central bank policy interest rate percentage for the requested period (current if no date) |
date | string | 2026-02-05 | Date when the rate data was recorded |
lastUpdated | string | 2026-02-05T05:00:00.000Z | ISO timestamp of the last data refresh update (current lookups only) |
lastChangedPremium | string | 2026-01-29 | Date when the rate was last changed (current lookups only) |
changePremium | number | -0.25 | Size of the last rate change in percentage points (current lookups only) |
changeDirection | string | down | Direction of last change: up, down, or unchanged (current lookups only) |
previousRatePremium | number | 4.75 | Rate before the last change (current lookups only) |
Why ground on it
A model can produce something that looks like this answer from its training data, and be confidently out of date or simply wrong. This source returns the current value in a shape you can check, which is the difference between an answer you can cite and one you have to hedge.
Point an evaluation at countryName: it is the field most worth pinning a claim to, and it is either present and current or absent — never plausibly invented.
Failure modes
Errors come back as tool errors carrying a sentence the model can act on, not a bare status code. Error handling covers the full list.
| Status | What it means |
|---|---|
400 / 422 | The arguments did not validate. The message names the offending one. |
401 | The OAuth session is invalid or expired — reconnect the server. |
403 | Blocked by a key restriction or an IP allow-list. Never a bad identity. |
404 | This source is not part of VerveContext. Check the catalog. |
429 | Out of credits, or a brief rate limit. The message tells them apart. |
A call costs 2 credits each time the tool actually runs; a model that reasons about the tool without calling it costs nothing.
Use cases
- Forex Trading Strategies
- Algorithmic currency traders evaluate interest rate differentials between countries to identify carry trade opportunities and adjust open positions before policy announcements.
- Fixed Income Portfolios
- When evaluating sovereign debt yields, bond portfolio managers compare current policy rates against benchmark curves to model duration risks across international markets.
- Macroeconomic Dashboards
- Financial media portals publish current central bank benchmark rates and recent change directions next to national inflation reports for market researchers.
- Loan Underwriting Calculations
- Calculate cross-border financing costs by feeding sovereign policy rates directly into commercial lending valuation models across 22 tracked economies.
Other ways to use Interest Rate Grounding Data
Set up Interest Rate Grounding Data on VerveContext, or reach the same source a different way. Your VerveContext account and credits work on all of them — one key, one balance.
Related
More in Finance: