# io.github.aurelio-nakamura/dataloupe

Offline MCP server to explore CSV/JSON/Parquet/Excel: preview, query, diff, render interactive HTML

- **Type:** MCP server
- **Trust:** 60/100 (B), scored on the content rubric
- **Verification:** community-indexed — nobody has claimed this listing
- **Version:** 0.15.0
- **Author:** io.github.aurelio-nakamura
- **License:** Unknown
- **Source:** https://github.com/aurelio-nakamura/dataloupe

## Trust

60/100 (B), scored on the content rubric
- Publisher verified: no
- Install scripts: nothing suspicious found
- Prompt-injection scan: clean
- Obfuscation scan: clean
- Evidence age: 0 days

## Security scan

- **Status:** clean
- **Scanned:** 2026-09-25T13:42:38.556Z
- **Version scanned:** HEAD
- **CVEs:** no coverage — this entry has no package coordinates to query OSV against, so "no known CVEs" is NOT asserted for it.

## Tools

7 declared. Statically extracted from the shipped source — a floor on the surface, not a census.
- `list_data_files` — List tabular data files (CSV/TSV/JSON/NDJSON/Parquet/Excel) in a local directory, with sizes.
- `describe_data` — Return the schema, row/column counts, and per-column statistics (type, nulls, unique, min/max/mean/median, top values) for a local data file. Token-efficient; r
- `preview_data` — Return the first N rows of a local data file as a Markdown table.
- `query_data` — Run a read-only structured query over a local data file: filter (where), select columns, order_by, limit/offset, and group_by with aggregations (count/sum/avg/m
- `sql_query` — Run a read-only SQL SELECT over a local data file and get a Markdown table back.
- `visualize_data` — Turn a local data file (optionally after a query) into ONE self-contained, fully-offline, interactive HTML explorer file on disk (sortable/filterable table + co
- `diff_data` — Compare two local data files (a git-style diff for data). Reports added/removed/changed/unchanged row counts (matched by --key when given), and optionally write

## Install

This entry has no npm package and no hosted endpoint, so there is nothing for an MCP client to launch or connect to. It is indexed as source only.

## Blast radius

Contained to extensive — no credential declaration found, from the publisher, the upstream registry, or the README. Known so far: reaches a data store.
- Floor 15, ceiling 45 (tier: unknown)
- `unknown` means the floor and ceiling land in different bands — not measured enough to name one. It does not mean low.
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/io.github.aurelio-nakamura%2Fdataloupe
- Install plan: https://forgeregistry.com/api/v1/packages/io.github.aurelio-nakamura%2Fdataloupe/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/io.github.aurelio-nakamura%2Fdataloupe
- HTML page: https://forgeregistry.com/registry/io.github.aurelio-nakamura%2Fdataloupe
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.