Worth Leaving
Server Details
Unvested-equity math: the verdict, what leaving forfeits, and the number an offer has to beat.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 2 tools
The two tools target entirely different questions: market base-pay benchmarking versus equity vesting/forfeit math for a leave decision. Each description explicitly states when to use it and defers to the other for the adjacent question (base pay vs. equity), leaving no plausible misselection.
Both names follow a snake_case verb_object pattern (check_market_base_pay, compute_walk_away_verdict) and are readable and self-describing. The only minor wrinkle is differing verb prefixes (check vs. compute) across just two tools, so there is little pattern to generalize.
Two tools is thin for a compensation-offer domain, even a narrowly scoped one, and there is no lighter-weight counterpart for partial questions. Each tool is substantive and deeply specified, so it is not an extreme mismatch, but the surface is borderline minimal.
The core decision loop (is my base at market, what does leaving cost in equity) is covered, but obvious adjacent operations are absent: no total-comp view (bonus is explicitly excluded), no offer-vs-offer comparison, and no cost-of-living or location-adjusted comparison. Agents asking those questions hit dead ends.
Available Tools
2 toolscheck_market_base_payMarket base pay checkARead-onlyIdempotentInspect
What a role and level earns in a US metro: median base salary from public US government data (H-1B filings and the BLS wage survey), with the middle half, the source and its date, and how a given base compares. Base pay only, equity and bonus excluded; an estimate, not a verdict, and it does not change compute_walk_away_verdict. Use it when the person asks whether their pay is at market, before or after the verdict.
Inputs: role (required), level (required), metro (required), base.
compute_walk_away_verdictWalk-away verdictARead-onlyIdempotentInspect
Call this instead of doing equity math. Give grant terms as written in the offer letter (shares or value, grant date, years, cliff, cadence monthly, quarterly or annual); do not pre-compute vest events. If the letter states per-year percentages, send them as yearlyPercents exactly as written. For options give shares, current price and strike. The offer is optional: with none, verdict is null, hasOffer is false, and the number to read is offerHasToBeat, what staying pays over the next year before tax. Returns the verdict, walkAwayCost (what leaving on the given date forfeits), nextVest, offerHasToBeat, leaveWindows (when leaving costs least in the two years after the leave date), levers (negotiation points the numbers support), the assumptions the engine filled in, and a shareable link that carries rounded bands only. If the person changes a price, a date or a term, call the tool again rather than scaling its numbers. For whether a base salary is at market for a role, level and metro, call check_market_base_pay.
Inputs: current (required), leaveDate (required), offer, filing, +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Equity comp tax/trade optimizer: ISO/AMT exercise, NSO, RSU, QSBS, concentration, hedging. 50-state.
Startup cap table: ownership, SAFEs, vesting and round modeling, plus drafts for admin approval.
Related MCP Servers
- AlicenseAqualityBmaintenanceDeterministic US equity-compensation tax optimizer. Six tools cover ISO/AMT exercise scheduling, NSO sell-vs-hold, RSU vest-and-sell, single-stock concentration, protective put / zero-cost collar pricing, and Section 1202 QSBS qualification. Federal plus 50-state plus DC tax math.8113 npm6MIT
- AlicenseAqualityDmaintenanceCost-of-living and quality-of-life comparison across ~165 cities: take-home pay, the equivalent salary you'd need, and the safety-net deltas (childcare, healthcare, vacation, parental leave).69 npm2MIT
- FlicenseNot gradedqualityCmaintenanceDeterministic tools for structuring high-stakes career and life decisions: cash-runway math with a safety floor, evidence grading (KNOWN/ASSUMED/UNKNOWN/SYNTHETIC) and six-dimension option comparison. Zero-dependency Python stdio server.-
- AlicenseAqualityBmaintenanceStartup valuation calculators for AI agents: 14 MCP tools covering 80+ formulas from the Startup Valuation textbook — probability, time value, CAPM, pre-revenue methods (Scorecard, Berkus, VC Method), options, comparables, SaaS, marketplace, fintech, biotech, hardware, international, stakeholder equity, and emerging methods.143MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.