Income Tax Grounding Data for AI Agents
The tool
Ground agents in verifiable US federal tax brackets from official sources so tax answers track real rates instead of stale memory.
Once your client is connected to the VerveContext MCP server, this appears in its tool list as IncomeTaxGroundingDataforAIAgents. 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.
{
"name": "IncomeTaxGroundingDataforAIAgents",
"arguments": {
"country": "US"
}
}What that looks like in a conversation
You don't name the tool — the model picks it. Asking about US in the terms this source covers is enough for it to reach for IncomeTaxGroundingDataforAIAgents on its own.
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 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.
| Argument | Type | Example | Description |
|---|---|---|---|
countryRequired | string | US | The country code (currently only 'US' is supported) |
yearPremium | integer | 2024 | The tax year to retrieve brackets for. Defaults to the previous year. |
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.
{
"status": "ok",
"error": null,
"data": {
"year": 2025,
"country": "US",
"type": "federal",
"brackets": {
"single": [
{
"rate": 0.1,
"min": 0,
"max": 11924
},
{
"rate": 0.12,
"min": 11925,
"max": 48474
},
{
"rate": 0.22,
"min": 48475,
"max": 103349
},
{
"rate": 0.24,
"min": 103350,
"max": 197299
},
{
"rate": 0.32,
"min": 197300,
"max": 250524
},
{
"rate": 0.35,
"min": 250525,
"max": 626349
},
{
"rate": 0.37,
"min": 626350,
"max": 999999999
}
],
"married_filing_jointly": [
{
"rate": 0.1,
"min": 0,
"max": 23849
},
{
"rate": 0.12,
"min": 23850,
"max": 96949
},
{
"rate": 0.22,
"min": 96950,
"max": 206699Fields
| Field | Type | Example | Description |
|---|---|---|---|
year | number | Tax year for the bracket data | |
country | string | Country code for tax data | |
type | string | Which tax the brackets describe, such as federal | |
brackets | object | Array of tax brackets with rates and income ranges | |
└ brackets.single | array[7] | Rate bands for a single filer | |
└ brackets.single.0.rate | number | Marginal rate for the band | |
└ brackets.single.0.min | number | Income at which the band starts | |
└ brackets.single.0.max | number | Income at which the band ends; null for the top band | |
└ brackets.married_filing_jointly | array[7] | Rate bands for married filers filing jointly | |
└ brackets.married_filing_jointly.0.rate | number | Marginal rate for the band | |
└ brackets.married_filing_jointly.0.min | number | Income at which the band starts | |
└ brackets.married_filing_jointly.0.max | number | Income at which the band ends; null for the top band | |
└ brackets.married_filing_separately | array[7] | Rate bands for married filers filing separately | |
└ brackets.married_filing_separately.0.rate | number | Marginal rate for the band | |
└ brackets.married_filing_separately.0.min | number | Income at which the band starts | |
└ brackets.married_filing_separately.0.max | number | Income at which the band ends; null for the top band | |
└ brackets.head_of_household | array[7] | Rate bands for a head of household filer | |
└ brackets.head_of_household.0.rate | number | Marginal rate for the band | |
└ brackets.head_of_household.0.min | number | Income at which the band starts | |
└ brackets.head_of_household.0.max | number | Income at which the band ends; null for the top band | |
standard_deduction | object | Standard deduction amounts by filing status | |
└ standard_deduction.single | number | ||
└ standard_deduction.married_filing_jointly | number | ||
└ standard_deduction.married_filing_separately | number | ||
└ standard_deduction.head_of_household | number | ||
lastUpdated | string | When the bracket table was last refreshed | |
marriagePenaltyPremium | object | Where filing jointly stops being worth twice a single filer's thresholds; null when the schedule doubles all the way up | |
└ marriagePenalty.appliesFromRatePremium | number | The rate band at which the doubling first breaks | |
└ marriagePenalty.singleThresholdPremium | number | Income at which a single filer enters that band | |
└ marriagePenalty.jointThresholdPremium | number | Income at which a couple filing jointly enters the same band | |
└ marriagePenalty.jointShortfallPremium | number | How far the joint threshold falls short of twice the single threshold | |
effectiveRateCurvePremium | object | Effective and marginal rate at a fixed ladder of incomes, for each filing status, showing the shape of the schedule | |
└ effectiveRateCurve.singlePremium | array[5] | ||
└ effectiveRateCurve.single.0.incomePremium | number | ||
└ effectiveRateCurve.single.0.taxableIncomePremium | number | ||
└ effectiveRateCurve.single.0.taxPremium | number | ||
└ effectiveRateCurve.single.0.effectiveRatePremium | number | ||
└ effectiveRateCurve.single.0.marginalRatePremium | number | ||
└ effectiveRateCurve.married_filing_jointlyPremium | array[5] | ||
└ effectiveRateCurve.married_filing_jointly.0.incomePremium | number | ||
└ effectiveRateCurve.married_filing_jointly.0.taxableIncomePremium | number | ||
└ effectiveRateCurve.married_filing_jointly.0.taxPremium | number | ||
└ effectiveRateCurve.married_filing_jointly.0.effectiveRatePremium | number | ||
└ effectiveRateCurve.married_filing_jointly.0.marginalRatePremium | number | ||
└ effectiveRateCurve.married_filing_separatelyPremium | array[5] | ||
└ effectiveRateCurve.married_filing_separately.0.incomePremium | number | ||
└ effectiveRateCurve.married_filing_separately.0.taxableIncomePremium | number | ||
└ effectiveRateCurve.married_filing_separately.0.taxPremium | number | ||
└ effectiveRateCurve.married_filing_separately.0.effectiveRatePremium | number | ||
└ effectiveRateCurve.married_filing_separately.0.marginalRatePremium | number | ||
└ effectiveRateCurve.head_of_householdPremium | array[5] | ||
└ effectiveRateCurve.head_of_household.0.incomePremium | number | ||
└ effectiveRateCurve.head_of_household.0.taxableIncomePremium | number | ||
└ effectiveRateCurve.head_of_household.0.taxPremium | number | ||
└ effectiveRateCurve.head_of_household.0.effectiveRatePremium | number | ||
└ effectiveRateCurve.head_of_household.0.marginalRatePremium | number | ||
changesPremium | object | How the table moved since the previous tax year; null when there is no prior year to compare against | |
└ changes.versusYearPremium | number | The tax year being compared against | |
└ changes.indexingPercentPremium | number | Average shift across every indexed threshold, which is the inflation adjustment the tax authority actually applied | |
└ changes.bracketShiftsPremium | object | Each band's threshold before and after, per filing status, with the percentage it moved |
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 with 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 type: 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 with a sentence the model can act on, not a bare status code.
| Status | What it means |
|---|---|
400 / 422 | The arguments didn't validate. The message names the offending one. |
401 | The OAuth session is invalid or expired — reconnect the server. |
403 | Out of credits. Not a bad key — the month's allowance is spent. |
404 | This source isn't part of VerveContext. Check the catalog. |
429 | Brief rate limit. Retrying after a moment succeeds. |
Other ways to use Income Tax Grounding Data for AI Agents
Set up Income Tax Grounding Data for AI Agents on VerveContext, or reach the same source a different way. Your VerveContext account and credits work on all of them — one key, one balance.
Frequently asked questions
Do I have to tell the agent to use IncomeTaxGroundingDataforAIAgents?
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 VerveContext 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.