Benchmark Rate SkillBenchmark Rate Skill

OnlineCredit Usage:1 per callTool:BenchmarkRateSkill

The tool

Give your agent the rates that replaced LIBOR. Call it as an MCP tool to read live SOFR, SONIA, ESTR, TONA and SARON.

Once your client is connected to the VerveKit MCP server, this appears in its tool list as BenchmarkRateSkill. It is read-only and open-world: it fetches, it never mutates anything on your side, so most clients will call it without asking you to confirm.

Tool call
{
  "name": "BenchmarkRateSkill",
  "arguments": {
    "rate": "SOFR"
  }
}

What that looks like in a conversation

You don't name the tool — the model picks it. Asking about SOFR in the terms this source covers is enough for it to reach for BenchmarkRateSkill on its own.

Connecting

One server URL covers every skill 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.

Client config
{
  "mcpServers": {
    "vervekit": {
      "url": "https://api.vervekit.com/v1/mcp"
    }
  }
}
Endpoint
https://api.vervekit.com/v1/mcp

Per-client setup — Claude Desktop, 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.

ArgumentTypeExampleDescription
rateRequiredstringSOFRThe benchmark rate to retrieve One of: SOFR, SONIA, ESTR, TONA, SARON.

What the model gets back

The result carries a structuredContent object matching the tool's declared outputSchema, so a client can read fields without parsing prose. status is "ok" on success and error is null; a null field means the value wasn't available for that input, not that the call failed.

Result
{
  "status": "ok",
  "error": null,
  "data": {
    "rate": "SOFR",
    "name": "Secured Overnight Financing Rate",
    "currency": "USD",
    "region": "United States",
    "administrator": "Federal Reserve Bank of New York",
    "value": 4.32,
    "date": "2026-02-04",
    "lastUpdated": "2026-02-05T05:00:00.000Z",
    "change1d": -0.01,
    "changeDirection": "down",
    "previousValue": 4.33,
    "previousDate": "2026-02-03"
  }
}

Fields

Fields marked Premium need a paid plan. On a plan without them the key is absent rather than wrong, so a model never reasons over a substituted value.
FieldTypeExampleDescription
ratestringSOFRBenchmark rate code (SOFR, SONIA, ESTR, TONA, SARON)
namestringSecured Overnight Financing RateFull name of the benchmark rate
currencystringUSDCurrency denomination of the benchmark rate
regionstringUnited StatesGeographic region where the rate applies
administratorPremiumstringFederal Reserve Bank of New YorkInstitution or entity administering the benchmark rate
valuenumber4.32Current benchmark rate percentage value
datestring2026-02-04Date of the benchmark rate value (YYYY-MM-DD format)
lastUpdatedPremiumstring2026-02-05T05:00:00.000ZLast update timestamp in ISO 8601 format
change1dPremiumnumber-0.01Rate change from previous day
changeDirectionstringdownDirection of daily change: up, down, or unchanged
previousValuePremiumnumber4.33Previous day's rate value
previousDatePremiumstring2026-02-03Previous data date (YYYY-MM-DD format)

Failure modes

Errors come back as tool errors with a sentence the model can act on, not a bare status code.

StatusWhat it means
400 / 422The arguments didn't validate. The message names the offending one.
401The OAuth session is invalid or expired — reconnect the server.
403Out of credits. Not a bad key — the month's allowance is spent.
404This skill isn't part of VerveKit. Check the catalog.
429Brief rate limit. Retrying after a moment succeeds.

Other ways to use Benchmark Rate Skill

Set up Benchmark Rate Skill on VerveKit, or reach the same source a different way. Your VerveKit account and credits work on all of them — one key, one balance.

Call it as a REST APIOne HTTPS endpoint and an X-API-Key header, with SDKs for Node, Python and .NET.APIVerveReference →
Use it in Google Sheets or ExcelA =VERVE() formula fills a column — no script, no export, recalculates in place.VerveSheetsReference →
Ground an agent on itA cited, machine-checkable fact your model can't produce on its own.VerveContextReference →

Frequently asked questions

Do I have to tell the agent to use BenchmarkRateSkill?

No. The tool's name and description are in the model's context once the server is connected, so it selects the tool when the question calls for it. Naming it explicitly works too and is useful when you want to force the call.

Does connecting the server expose every tool at once?

Yes — one connection lists the whole VerveKit catalog. Clients with a tool budget can usually filter the list; the credit cost is per call, so an unused tool costs nothing.

What does a call cost?

1 credit each time the tool actually runs. A model that reasons about the tool without calling it costs nothing.

Is there a REST version of this?

Yes — the same source is available as a plain HTTPS endpoint on APIVerve, linked above. Same data, same credits, same account.

What's Next?

Continue your journey with these recommended resources

Was this page helpful?