IRS-audit-proof mileage tracker. Log every deductible mile in your AI client
About
Local-first MCP server for tracking deductible vehicle mileage. Every trip lives in a SQLite database on your laptop. Tax-year deductions are computed using the actual IRS standard mileage rate for that year — public-domain data, baked in.
What it does: • Log trips by talking to your AI client: date, miles, category (business / medical / moving / charitable), purpose • Manage multiple vehicles with default-vehicle support • Year-start / year-end odometer snapshots (IRS substantiation) • Annual deduction calc: miles × IRS rate for that tax year → Schedule C line 9 number • Mileage summary by date range / category / vehicle • Audit-trail CSV export: Date, Miles, Category, Purpose, Start, End, Vehicle, Notes
How it works: 14 MCP tools. Local SQLite. IRS standard mileage rates baked in for tax years 2022-2026 (annual update shipped within 1 week of IRS publication). Strict input validation: ISO date format, positive miles, plausibility caps, category enum.
Who it's for: • 15M+ US Schedule C filers (freelancers, contractors, small business owners) • 8M+ gig drivers (Uber/Lyft/DoorDash/Instacart) who need mileage logs for their 1099 income • Anyone tracking medical or charitable miles for itemized deductions
Why this instead of MileIQ / Everlance / Driversnote: • One-time install, no $5-10/mo subscription • Lives in your AI client — log trips by talking, not by tapping • Local-first — your trip data stays on your machine • Open source under BSL-1.1
Compliance notes: • Software, not tax advice. Verify deductions with a CPA before filing. • IRS rules require choosing standard-mileage vs actual-expense in Year 1 of vehicle service.
Security Report
Valid MCP server (4 strong, 7 medium validity signals). 3 known CVEs in dependencies (1 critical, 2 high severity) ⚠️ Package registry links to a different repository than scanned source. Imported from the Official MCP Registry. 1 finding(s) downgraded by scanner intelligence.
10 files analyzed · 4 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
Permissions Required
This plugin requests these system permissions. Most are normal for its category.
What You'll Need
Set these up before or after installing:
Environment variable: MCP_LICENSE_KEY
Purchase above for keyEnvironment variable: STITHY_MILEAGE_DB
Sign up freeHow to Install
Install instructions and configuration are available after purchase.
Getting Started
Once installed, try these example prompts and explore these capabilities:
- 1"Add my truck: 2019 Toyota Tacoma, set as default"
- 2"I drove 23 miles today for a client visit downtown — log it"
- 3"Show me my business mileage for March"
- 4"What's my Schedule C mileage deduction for tax year 2025?"
- 5"Export my 2026 trips as a CSV"
- 6"Log my year-end odometer reading: 67,432 miles"
- 7Tool: add_trip — Log a trip with date, miles, category, purpose
- 8Tool: annual_deduction — IRS-rate × miles → Schedule C number for any tax year
- 9Tool: export_csv — Audit-trail CSV with Date, Miles, Category, Purpose, Vehicle
- 10Tool: mileage_summary — Sum miles per category for any date range
- 11Tool: irs_rates — Reference table of IRS standard mileage rates by year
Reviews
No reviews yet
Be the first to review this server!
More Productivity MCP Servers
Memory
Freeby Modelcontextprotocol · Productivity
Knowledge graph-based persistent memory across sessions
Time
Freeby Modelcontextprotocol · Productivity
Time and timezone conversion capabilities for your AI assistant
Toleno
Freeby Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
mcp-creator-python
Freeby mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.
MCP Marketplace
Freeby mcp-marketplace · Developer Tools
Search and install MCP servers from inside your AI client.
MarkItDown
Freeby Microsoft · Content & Media
Convert files (PDF, Word, Excel, images, audio) to Markdown for LLM consumption