Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@statetakehome-mcp Compute take-home pay for 75000 salary in California as single"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol (MCP) server that puts a full US paycheck-tax engine directly at your AI assistant's fingertips: federal brackets, all 50 states + DC, FICA, self-employment tax, and capital gains — all for the 2026 tax year, and all sourced from the same engine that powers statetakehome.com.
Why it's different: most take-home-pay calculators stop at "gross minus taxes." This one also understands the 2026 OBBBA (One Big Beautiful Bill Act) landscape — the current-year federal brackets and thresholds it ships with already reflect the post-OBBBA baseline, so estimates stay accurate as the rules that shaped the 2026 tax year continue to roll out.
No installation needed — run it with npx.
Add to your MCP config (claude_desktop_config.json or .mcp.json):
{
"mcpServers": {
"statetakehome": {
"command": "npx",
"args": ["-y", "statetakehome-mcp"]
}
}
}Add to .cursor/mcp.json:
{
"mcpServers": {
"statetakehome": {
"command": "npx",
"args": ["-y", "statetakehome-mcp"]
}
}
}Restart your client and the three tools below become available.
Related MCP server: OpenAccountants
us_take_home_payNet pay for a US W-2 employee: federal income tax, state income tax (all 50 states + DC), Social Security, Medicare, Additional Medicare, and state-specific extras (CA SDI, OR transit tax, etc.). Handles pre-tax 401(k) and health-insurance deductions and returns a per-paycheck breakdown for every pay frequency.
Example call:
{
"gross": 75000,
"state": "CA",
"filingStatus": "single"
}Response (abridged, from the live engine):
{
"result": {
"gross": 75000,
"federalTax": 7670,
"stateTax": 2940.85,
"socialSecurity": 4650,
"medicare": 1087.5,
"totalTax": 17323.35,
"takeHome": 57676.65,
"effectiveRate": 0.2310,
"perPaycheck": { "biweekly": 2218.33, "monthly": 4806.39 }
}
}The same input with "state": "TX" (no state income tax) returns stateTax: 0 and takeHome: 61592.5 — $3,915.85 higher on the same gross pay.
self_employment_taxSchedule SE self-employment tax (15.3% on 92.35% of net profit, split into the Social Security and Medicare portions), the 0.9% Additional Medicare surtax, federal income tax, an optional state income tax, and a quarterly estimated-payment figure.
Example call:
{
"netProfit": 90000,
"filingStatus": "single",
"state": "TX"
}Response (abridged, from the live engine):
{
"result": {
"netProfit": 90000,
"seTax": 12716.6,
"seTaxDeduction": 6358.3,
"federalIncomeTax": 9571.17,
"totalTax": 22287.77,
"quarterlyEstimate": 5571.94,
"setAsidePct": 0.2477
}
}capital_gains_taxFederal capital gains tax — long-term stacked 0%/15%/20% bands or short-term ordinary rates — plus the 3.8% Net Investment Income Tax (NIIT) above the MAGI threshold, and an optional state estimate (most states tax gains as ordinary income).
Example call:
{
"gain": 50000,
"ordinaryTaxableIncome": 80000,
"filingStatus": "single",
"term": "long"
}Response (abridged, from the live engine):
{
"result": {
"gain": 50000,
"taxableGain": 50000,
"federalTax": 7500,
"niit": 0,
"totalTax": 7500,
"netProceeds": 42500,
"ltcgRate": 0.15
}
}Tax year: 2026.
Federal brackets & standard deduction: IRS Rev. Proc. 2025-32.
State brackets & standard deductions: Tax Foundation — State Individual Income Tax Rates and Brackets, as of January 1, 2026, cross-checked against individual state Departments of Revenue.
FICA: current Social Security wage base and Medicare rates, including the 0.9% Additional Medicare surtax.
Capital gains: long-term bands and the NIIT threshold per Rev. Proc. 2025-32, cross-checked against Tax Foundation and Schwab.
Every response includes a source block naming the underlying publication and a reference_url pointing to the matching calculator on the live site for further reading and methodology notes:
The calculation code in this package is the same engine that runs statetakehome.com, kept in sync by hand — it is not a reimplementation.
This tool produces estimates for planning purposes only. It is not tax advice. Tax situations vary; consult a licensed CPA or tax professional before making financial decisions.
MIT © tresor4k
Computes federal capital gains tax (long-term 0%/15%/20% stacked bands or short-term ordinary rates), the 3.8% Net Investment Income Tax (NIIT) above the MAGI threshold, and an optional state income tax on the gain (states generally tax capital gains as ordinary income). Example input: { "gain": 50000, "ordinaryTaxableIncome": 80000, "filingStatus": "single", "term": "long" }. 2026 tax year — estimates, not tax advice; thresholds from Rev. Proc. 2025-32, cross-checked against Tax Foundation & Schwab.
| Name | Required | Description | Default |
|---|---|---|---|
| gain | Yes | Gross capital gain in USD (sale price minus cost basis), e.g. 50000. | |
| term | Yes | "long" for assets held > 1 year (preferential rates), "short" for ordinary rates. | |
| state | No | Optional two-letter US state or DC postal code; most states tax the gain as ordinary income. | |
| exclusion | No | Amount excluded from the gain before tax (e.g. the §121 primary-residence sale exclusion). | |
| filingStatus | Yes | IRS filing status. | |
| ordinaryTaxableIncome | Yes | Other taxable income (excluding the gain), which sets the long-term capital gains bracket and NIIT threshold. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It indicates the tool computes estimates and is not tax advice, but does not explicitly state it is read-only or non-destructive. Implicitly, it is a calculator with no side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single dense sentence that packs all necessary information. While efficient, it could be slightly restructured for readability, but it earns its place without excess.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (multiple tax components, optional state tax) and lack of output schema, the description does not specify the output format or breakdown. It covers inputs well but leaves output details unclear.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, providing baselines of 3. The description adds value by providing an example input and clarifying the 'gain' parameter as gross gain. It also mentions the §121 exclusion, adding context beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool computes federal capital gains tax, NIIT, and optional state tax, and distinguishes itself from sibling tools (us_take_home_pay, self_employment_tax) by focusing on capital gains specifically.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description includes an example input and specifies the tax year (2026) and that it provides estimates, not advice. It lacks explicit 'when to use' vs. alternatives, but the tool name and context make it clear for capital gains situations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Computes Schedule SE self-employment tax (15.3% = 12.4% Social Security up to the wage base + 2.9% Medicare on 92.35% of net profit), the Additional Medicare surtax, federal income tax, and an optional state income tax, plus a quarterly estimated-payment figure. Example input: { "netProfit": 90000, "filingStatus": "single", "state": "TX" }. 2026 tax year — estimates, not tax advice; brackets from Tax Foundation (Jan 1, 2026) & IRS.
| Name | Required | Description | Default |
|---|---|---|---|
| state | No | Optional two-letter US state or DC postal code to also estimate state income tax. | |
| netProfit | Yes | Schedule C net profit in USD (1099 income minus business expenses), e.g. 90000. | |
| otherIncome | No | Other ordinary income (e.g. a W-2 job) that stacks on top for bracket and wage-base purposes. | |
| filingStatus | Yes | IRS filing status. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses tax year (2026), source (Tax Foundation & IRS), and adds disclaimer ('estimates, not tax advice'). It also includes example input and explains the tax breakdown, making behavior transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is a single paragraph that packs dense information (tax breakdown, formula, example, year, source) without being overly verbose. Could potentially be split for readability, but it is concise and front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (4 parameters, multiple tax calculations, optional state tax), the description covers the main functionality well. No output schema, but it mentions quarterly estimated-payment figure. Disclaimers and example enhance completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. The description does not add extra parameter-level information beyond what the schema already provides (e.g., enum descriptions). Schema already explains netProfit, filingStatus, state, otherIncome clearly.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it computes Schedule SE self-employment tax (with breakdown), Additional Medicare surtax, federal income tax, optional state tax, and quarterly estimated payments. It distinguishes from sibling tools like us_take_home_pay and capital_gains_tax by specificity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Description explains the tool computes self-employment taxes and when it's appropriate. It lacks explicit exclusions or comparisons to siblings, but the purpose is clear and context signals provide sibling names. The example input helps understand usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Computes net take-home pay for a US W-2 employee: federal income tax, state income tax (all 50 states + DC), FICA (Social Security + Medicare + Additional Medicare), and state-specific extras (e.g. CA SDI, OR transit tax). Supports pre-tax 401(k) and health-insurance deductions and per-paycheck breakdowns. Example input: { "gross": 75000, "state": "CA", "filingStatus": "single" }. 2026 tax year — estimates, not tax advice; brackets from Tax Foundation (Jan 1, 2026) & IRS.
| Name | Required | Description | Default |
|---|---|---|---|
| gross | Yes | Annual gross income in USD, e.g. 75000. | |
| state | Yes | Two-letter US state or DC postal code, e.g. "CA", "TX", "NY". | |
| dependents | No | Number of dependents claimed (informational; not currently used in the federal/state bracket math). | |
| filingStatus | Yes | IRS filing status. | |
| payFrequency | No | Pay frequency; the result always includes a full per-paycheck breakdown for all frequencies regardless of this value. | |
| pretax401kPct | No | Pre-tax 401(k) contribution as a percent of gross pay (0-100), capped at the 2026 employee deferral limit ($23,500). | |
| pretaxHealthAnnual | No | Annual pre-tax health insurance / HSA premiums in USD, excluded from both income tax and FICA wages. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses coverage (federal, state, FICA, state-specific extras), pre-tax deductions, per-paycheck breakdown, example input, tax year, and a disclaimer about estimates. It does not mention if the tool is read-only, but as a calculator this is implicit.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single paragraph with several sentences, no wasted words. It is front-loaded with the primary action. Some bullet-point structuring could improve scannability, but it remains concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description outlines what the tool computes and includes an example input, but without an output schema, it does not describe the return structure (e.g., named fields, per-paycheck items). For a calculator returning detailed breakdowns, this is a notable gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description adds context by listing the tax components and mentioning pre-tax deductions, but the parameter descriptions in the schema are already detailed. The extra value is moderate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description specifies a precise verb ('Computes net take-home pay') and resource ('US W-2 employee'), lists covered taxes and deductions, and inherently distinguishes from siblings (self-employment and capital gains taxes).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description clearly defines the tool's scope (W-2 employees, 2026 tax year) and lists what it includes, which implies when to use it. However, it does not explicitly contrast with sibling tools or state when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.1capital_gains_taxself_employment_taxus_take_home_payEach tool targets a distinct tax scenario: W-2 employment, self-employment, and capital gains. No overlap in purposes.
All names follow a consistent snake_case pattern describing the tax type (e.g., us_take_home_pay, self_employment_tax, capital_gains_tax).
3 tools is low but appropriate for a focused tax calculator; covers the most common income types without being too sparse.
Covers W-2, self-employment, and capital gains, but omits other income types like dividends, rental income, and business income beyond self-employment.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Current source-cited 2026 US tax constants and calculators for AI agents; every answer cites IRS.
Live US paycheck and payroll-tax math for 2026, all 50 states and DC, powered by tools-berry.com.
Verifiable US tax oracle for AI agents: cited, machine-checkable federal and state tax computation
# TrueCalci Precision Compute Engine Deterministic statutory, financial, and engineering computational tools for AI agents, developers, and autonomous workflows over the Model Context Protocol (MCP). ### Capabilities (25 Verified Engines): - **Specialist FinOps:** Remote Contractor vs. W-2 Parity, S-Corp Reasonable Compensation (IRS Rev. Rul. 74-44), Solo 401(k) Shelter, Cross-Border FX Drag, Billable Capacity Floor. - **Global & Cross-Border Tax:** US Form 2555 FEIE Nomad Stacking, B2B Foreign
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/tresor4k/statetakehome-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
