WDI is a local MCP server that helps structure high-stakes career and life decisions with checklists, runway math, evidence grading, and weighted option comparison.
Return a six-dimension decision checklist covering cash runway, time windows, care load, safety floor, control rights, and institutional bridges, plus evidence tiers and a step-by-step process.
Calculate months of cash runway after a change, including one-time costs, new monthly costs, income after the change, and a safety-floor buffer.
Grade decision claims as KNOWN, ASSUMED, UNKNOWN, or SYNTHETIC and suggest next steps.
Rank two or more options scored 1–5 across the six dimensions, with optional weights; any option with a redline score of 1 is ranked last.
All tools are read-only and run locally via MCP.
An open-source Model Context Protocol server that helps Claude, Cursor or any MCP client structure high-stakes career and life decisions with numbers and evidence instead of generic reassurance: quitting a "golden handcuffs" job, taking a career break for caregiving, relocating, or weighing a family promise against what you actually control.
Zero dependencies, Python 3.10+, everything runs locally.
Tool | What it does |
| The six questions to answer for every option: cash runway, irreversible time windows, care load, safety floor (health insurance, housing), actual control rights, institutional bridges (leave, severance, part-time). |
| Months of runway after a change, the cash needed for a safety floor (default 6 months of essentials), and how long you can experiment before touching it. |
| Tags each claim behind the decision as |
| Ranks 2+ options scored 1-5 on the six dimensions with optional weights. An option with a redline (score 1, e.g. losing health insurance) is ranked last regardless of its average. |
Related MCP server: wellcontrol.mcp_server
git clone https://github.com/alicexixi85/wdi-decision-mcp.git{
"mcpServers": {
"wdi": {
"command": "python3",
"args": ["/absolute/path/to/wdi-decision-mcp/server.py"]
}
}
}Docker: docker build -t wdi-decision-mcp . && docker run -i --rm wdi-decision-mcp
"I have $40k in savings, $3,500 of essential costs a month and would earn $1,000 freelancing. If I quit, how long is my runway with a 6-month safety floor?"
"Grade the evidence: my manager promised a promotion next year; the offer letter says $120k; I don't know the severance policy."
"Compare staying, a 4-day week, and quitting across the six dimensions."
There is also a no-install version of the method in wdi_lite_prompt.md that you can paste into any chat assistant.
This is a decision-structuring aid. It is not legal, tax, financial, medical or mental-health advice. For contracts, prenups or divorce, taxes, benefits or safety concerns, talk to a qualified professional. If you are in danger, contact local emergency services.
This repository is complete and free (MIT). The separate paid WDI 2.4.3 toolkit ($35, Gumroad) is a 75-file bilingual (EN/ZH) skill package for AI agents: a root SKILL file, research profiles, frameworks and playbooks, synthetic decision-card examples and jurisdiction-sensitive research cards (marked as needing verification).
MIT
Compute months of cash runway after a change (quitting, pay cut, relocation, career break) and how long until a safety floor is reached.
Inputs: liquid_cash (required), monthly_essential_costs (required), one_time_costs, extra_monthly_costs, +2 more.
Rank 2+ options scored 1-5 on the six dimensions (5 = best for you), with optional weights; options with a redline (score 1) are ranked last.
Inputs: options (required), weights.
Tag each claim behind a decision as KNOWN, ASSUMED, UNKNOWN or SYNTHETIC and suggest the next step for each.
Inputs: claims (required).
Return the six-dimension decision checklist (cash runway, time windows, care load, safety floor, control rights, institutional bridges), the four evidence tiers and a step-by-step process.
Inputs: decision.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 4 tools
Each tool has a distinct action: returning static framework content, a cash calculation, evidence tagging, and option ranking. The only mild overlap is that six_dimension_checklist supplies the dimensions and tiers that compare_options and grade_evidence consume, but the actions themselves are clearly separable.
Three of four names follow a clean verb_noun pattern (calculate_runway, grade_evidence, compare_options). six_dimension_checklist is a noun phrase for a retrieval tool, which is a readable and defensible deviation but breaks the otherwise uniform convention.
Four tools is a tight, well-scoped set for a single decision-analysis workflow with no redundant entries. It sits at the low end of the comfortable range, so the surface feels minimal rather than generous.
The core workflow (get framework, grade evidence, compute runway, rank options) is covered end to end. Gaps remain in persistence and synthesis: there is no tool to save a decision, retrieve prior assessments, or produce a final recommendation summary, though an agent can assemble those itself.
Verifiable, deterministic risk math for autonomous agents; re-runnable proof on every answer.
Deterministic multi-criteria decision analysis for AI agents — score, rank & explain options.
Deterministic reasoning stack for AI agents: simulate, decide & compute, plus cross-domain tools.
Deterministic sealed verdicts on public claims and startup ideas (0-LLM claim-safety guardian).
