mcpField
S
Sheet & Flow Landlord Math

Sheet & Flow Landlord Math

Local
onyxaholguin-cyber.github.ioBusiness & Marketing0Updated 1w ago

About Sheet & Flow Landlord Math

Sheet & Flow Landlord Math is an offline MCP server that provides deterministic rental-property and landlord calculations. It serves landlords and property analysts with tools for cash flow, financing, short-term rentals, late fees, lease notices, and mileage deductions.

Key features

  1. 01Rental property cash-flow and return metrics
  2. 02Mortgage payment calculations
  3. 03Short-term rental break-even analysis
  4. 04Late-fee calculation with optional state examples
  5. 05Lease notice dates and mileage deduction

Use cases

  1. 01Evaluate rental-property cash flow and DSCR
  2. 02Estimate Airbnb break-even occupancy or nightly rate
  3. 03Calculate a late fee using a grace period and cap
  4. 04Find a lease renewal notice date

MCP support

Provides MCP tools for rental-property analysis, mortgage payments, short-term rental analysis, late fees, lease renewal notices, and the 2026 IRS mileage deduction. It runs locally without network calls or API keys.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository
Packages
mcpbsheet-and-flow-mcp-1.0.0.mcpb

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Sheet & Flow Landlord Math (MCP server)

Landlord and rental-property calculators as Model Context Protocol tools, so Claude, Cursor, VS Code or any MCP client does the math the same way every time instead of estimating it.

  • Offline and deterministic. No network calls, no API keys, no data leaves your computer.
  • No dependencies. Plain Node.js (18+), about 380 lines you can read.
  • Tested. 552 randomized cases against an independent Python model, and the worked examples from the Sheet & Flow tutorials, on Node 18, 20 and 22 in CI. The rental math was also cross-checked against spreadsheet-recalculated (LibreOffice) deals before release.

Tools

ToolWhat it answers
rental_property_analysisYear-one NOI, monthly and annual cash flow, cap rate, cash-on-cash, DSCR, gross rent multiplier, break-even occupancy, expense ratio
mortgage_paymentMonthly principal and interest, total interest
short_term_rental_analysisAirbnb/VRBO booked nights, stays, gross revenue, cash flow, RevPAR, what each booked night is worth, break-even occupancy and break-even nightly rate
rent_late_feeDays late and the late fee: grace period, flat + percent + daily fees, a cap; optional Colorado / New York / Texas examples
lease_renewal_noticeDate the renewal or rent-increase notice must go out, 0-30/31-60/61-90 day window, status, next lease end
irs_mileage_deduction_20262026 IRS standard mileage deduction (business 72.5¢ Jan–Jun, 76¢ Jul–Dec)

Percentages are fractions (0.25 = 25%). Dates are YYYY-MM-DD. A percentage passed as 7 instead of 0.07 is rejected with a clear message rather than silently computed.

Install

Claude Desktop (one click): download sheet-and-flow-mcp-<version>.mcpb from the latest release and open it.

Any MCP client (stdio): clone the repo and point your client at server/index.js:

{
  "mcpServers": {
    "sheet-and-flow": { "command": "node", "args": ["/path/to/sheet-and-flow-mcp/server/index.js"] }
  }
}

Docker: docker build -t sheet-and-flow-mcp . then use {"command": "docker", "args": ["run", "-i", "--rm", "sheet-and-flow-mcp"]} in your client config.

It is also listed in the official MCP Registry as io.github.onyxaholguin-cyber/sheet-and-flow-mcp.

Install as an agent plugin (Grok Build, Cursor, Claude Code)

This repo is also a plugin: the MCP server plus three skills that tell the agent when and how to use it.

SkillUse it for
landlord-deal-analysis"Does this duplex / Airbnb cash flow?", cap rate, cash-on-cash, DSCR, break-even occupancy
rent-late-feeDays late and the late fee, with optional Colorado, New York and Texas limits
lease-renewal-noticeWhen the renewal or rent-increase notice must go out, for one lease or a list

Manifests: .grok-plugin/plugin.json, .cursor-plugin/plugin.json, .claude-plugin/plugin.json; MCP config: .mcp.json.

Privacy and terms: PRIVACY.md (no data collected).

Network and credentials (declared for reviewers): none at run time. The server makes no network calls, reads no files and needs no API key or account. At install time, .mcp.json runs npx -y github:onyxaholguin-cyber/sheet-and-flow-mcp#<full commit sha>, which downloads this repo at that exact pinned commit from GitHub (the package has zero dependencies). test/plugin_check.py fails CI if the pinned commit's server/ differs from the tested code.

Example

Ask: "Airbnb deal: $350,000, 25% down at 7%, $185 a night, 62% occupancy, 14 blocked nights, 3.2-night stays, $95 cleaning fee, $85 cleaning cost, 15.5% host fee, 9% maintenance, $920/month fixed costs, $10,500 closing, $25,000 furnishing. Does it cash flow?"

short_term_rental_analysis returns, among other fields:

{ "monthlyCashFlow": -208.64, "keptPerBookedNight": 135.53, "breakEvenOccupancy": 0.6726, "breakEvenNightlyRate": 200.24 }

So the deal loses about $209 a month as quoted; it needs 67.3% occupancy at $185, or $200.24 a night at 62%. The same example is worked step by step in the short-term rental calculator tutorial.

How the math works

Every formula is explained in a free tutorial:

Prefer a spreadsheet?

The same math comes as finished Excel / Google Sheets workbooks from Sheet & Flow (paid; this server is free and MIT-licensed and doesn't need them): Short-Term Rental Deal Analyzer · Rental Property Deal Analyzer · Landlord Tenant Toolkit · Lease Renewal Tracker · Freelancer Mileage Log · Free Rental Cash Flow Calculator

Development

npm test                       # node --test, no install step
python3 test/model.py          # regenerate fixtures from the independent Python model
python3 scripts/build_mcpb.py  # build dist/*.mcpb and dist/server.json

Releases: pushing a v* tag runs the tests, builds the .mcpb, attaches it to a GitHub release and publishes server.json to the MCP Registry with GitHub OIDC (no stored tokens).

Disclaimer

Estimates for planning only. Not legal, tax or investment advice. The late-fee state examples are a summary of statute text as of October 2026; check current law, city rules and your lease before charging a fee.

MIT License © Sheet & Flow

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.