
gnomon
Exposes deterministic Python implementations for date arithmetic, calendar operations, and math so Claude stops next-token-guessing numbers that matter. The `now()` tool returns 18 fields in one call (ISO week, quarter, fiscal year, weekday). The `calendar(ops)` tool batches date operations (diff, until, since, add, business_days, parse natural language like "next thursday") across table rows. The `calc(expressions)` tool evaluates Python math with preloaded functions (sqrt, sin, mean, stdev) and takes lists in, lists out. Unit conversion via Pint handles kg to lb, Celsius to Fahrenheit, meters to feet. Reach for this when you need Claude to compute instead of hallucinate, especially across month boundaries, with decimals, or when processing columns of a dataset where small errors compound.
- tools
- 4
- transport
- STDIO
- last updated
- May 25, 2026
Tools
4 toolsPublic tool metadata for what this MCP can expose to an agent.
nowReturns a rich dict snapshot of the current moment.
Returns a rich dict snapshot of the current moment.
No parameter schema in public metadata yet.
calendarBatch dispatcher where each item picks its own op (diff, until, since, add, weekday, business_days, parse, format).
Batch dispatcher where each item picks its own op (diff, until, since, add, weekday, business_days, parse, format).
No parameter schema in public metadata yet.
calcEvaluates a list of Python expressions and returns a list of results, with math, statistics and common builtins pre-loaded.
Evaluates a list of Python expressions and returns a list of results, with math, statistics and common builtins pre-loaded.
No parameter schema in public metadata yet.
calc_convertUnit conversion via Pint (e.g. meter to foot, kg to lb, degC to degF).
Unit conversion via Pint (e.g. meter to foot, kg to lb, degC to degF).
No parameter schema in public metadata yet.
Sponsors
Readme
gnomon-mcp
The pointer on a sundial that turns shadow into time.
A small MCP server for the boring-but-essential utilities every model needs: dates, calendars, arithmetic, unit conversion. Use it so your assistant stops "next-token guessing" math and date math.
Why
LLMs are bad at arithmetic and date math by default. They produce plausible answers that are often wrong by a small amount — exactly the kind of mistake that's hard to notice in a long response. gnomon-mcp exposes deterministic Python implementations through MCP so your model can compute instead of guess.
When an agent should reach for gnomon
Anywhere the next plausible token is not the right answer. Concretely:
Details
- Repository
- github.com/lihtness/gnomon-mcp
- Category
- AI & LLM Tools
- Package
gnomon-mcp- Transport
- STDIO
- Registry
- MCP registry, active