Jdatamunch Mcp

Quickstart - https://github.com/jgravelle/jdatamunch-mcp/blob/main/QUICKSTART.md

FREE FOR PERSONAL USE

**Use it to make money, and Uncle J. gets a taste. Fair enough?** [details](#commercial-licenses)

---

Documentation

Doc	What it covers
QUICKSTART.md	Zero-to-indexed in three steps
USER-MANUAL.md	Full guide for analysts, ops, and non-developers

---

Cut spreadsheet token usage by **99.997%**

Most AI agents explore tabular data the expensive way:

dump the whole file into the prompt → skim a million irrelevant rows → repeat.

That is not "a little inefficient." That is a **token incinerator**.

A 255 MB CSV file with 1 million rows costs **111 million tokens** if you paste it raw. A single `describe_dataset` call answers the same orientation question in **3,849 tokens**.

That is a **25,333× reduction** — measured, not estimated, on a real 1M-row public dataset.

**jDataMunch indexes the file once and lets agents retrieve only the exact data they need**: column profiles, filtered rows, server-side aggregations, cross-dataset joins, and semantic search — with SQL precision.

**Benchmark:** LAPD crime records — 1,004,894 rows, 28 columns, 255 MB Baseline (raw file): 111,028,360 tokens  |  jDataMunch: ~3,849 tokens  |  **25,333× reduction** [Methodology & harness](benchmarks/METHODOLOGY.md) · [Full results](benchmarks/results.md)

Task	Traditional approach	With jDataMunch
Understand a dataset	Paste entire CSV	describe_dataset → column names, types, cardinality, samples
Find relevant columns	Read every row	search_data → column-level results with IDs
Answer a filtered question	Load millions of rows	get_rows with structured filters → only matching rows
Compute a group-by	Return all data	aggregate → server-si