
Estimate My Paycheck MCP server
Which MCP servers are Estimate My Paycheck's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-29
- Registry namecom.estimatemypaycheck/paycheckverified in the MCP registry
The registry name sits under estimatemypaycheck.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-29
- Tools3
- Server calls itselfestimatemypaycheck
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-29 the server answered initialize and tools/list without a sign-in. First answer in 52 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 6 of the 7 days it takes to judge reliability.
Once connected
- For "compare take-home pay across US states for one salary", the likely first call is compare_states.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 6 so far
- Answeredmeasuring6 of the 7 daily checks it takes to print a share
- Median first answer78 ms
- Space in an agent's context≈ 824 tokensthe definitions of all its tools (3), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 3 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- can do · compare take-home pay across US states for one salary
- not sure · estimate paycheck effect of 401(k) contributions
- not sure · check federal withholding against a W-4 form
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
calculate_paycheckCompute a US paycheck for 2026: gross, each tax and pre-tax deduction, and take-home pay per paycheck and per year, for a salary or an hourly rate (overtime over 40 hours at 1.5 times) in any state or DC. Federal withholding follows the…
compare_statesTake-home pay for the same salary in the 50 states and DC in 2026, sorted from the highest. Useful to answer "which state lets me keep the most" or to price a move.
calculate_bonus_taxWhat a bonus check pays after the flat 22% federal supplemental withholding, FICA and state tax, and how much of the federal withholding comes back (or is still owed) at tax time, on top of a salary, 2026 rules (IRS Pub. 15).
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"paycheck": {
"type": "http",
"url": "https://estimatemypaycheck.com/api/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http estimatemypaycheck https://estimatemypaycheck.com/api/mcpclaude.ai, ChatGPT and other clients: add https://estimatemypaycheck.com/api/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.