latbert avatar

tabular-mcp

latbert/tabular-tools

CSV/JSONL/xlsx toolkit: schema inference, dirty-row reports, format conversion, seeded sampling

tools
3
transport
STDIO
last updated
Nov 16, 2026

Tools

3 tools

Public tool metadata for what this MCP can expose to an agent.

tabular_inspectInspect a local CSV / JSONL / xlsx file: row count, column list, inferred schema (per-column dominant type + full type distribution + empty counts) and a dirty-row report with 1-based file row numbers.

Inspect a local CSV / JSONL / xlsx file: row count, column list, inferred schema (per-column dominant type + full type distribution + empty counts) and a dirty-row report with 1-based file row numbers.

No parameter schema in public metadata yet.

tabular_convertConvert csv → jsonl, jsonl → csv, xlsx → csv/jsonl, returning content inline and optionally writing to a path.

Convert csv → jsonl, jsonl → csv, xlsx → csv/jsonl, returning content inline and optionally writing to a path.

No parameter schema in public metadata yet.

tabular_sampleStream-sample without loading the file: head / tail / seeded random, with each sampled row carrying its file row number.

Stream-sample without loading the file: head / tail / seeded random, with each sampled row carrying its file row number.

No parameter schema in public metadata yet.

Sponsors

Readme

tabular-tools

Deterministic tabular-file tools for agents and humans: CSV / JSONL / xlsx local read → validate → convert → sample, as an npm engine (@nopilot/tabular-engine) plus a local-first MCP server (@nopilot/tabular-mcp).

Why not just "read the file"? Agents burn context reading raw files and still miscount rows, miss dirty rows, and mangle quoted CSV. These tools do it deterministically: same input → byte-identical output, every time.

The local-first difference

Most tabular-file MCP servers in the wild (e.g. the Pipeworx "CSV Tools" family, ~235 weekly visitors) run behind a hosted gateway: your file leaves your machine, hits their servers, and comes back. That is a non-starter for anything proprietary, personal, or offline.

tabular-mcp runs entirely on your machine:

hosted CSV/xlsx MCP serverstabular-mcp
Where your data goesuploaded to their gatewaynever leaves the process
Works offlinenoyes
Extra accounts / API keysusually yesnone
Deterministic outputnot guaranteedbyte-identical (seeded sampling)
Source availablemostly closedMIT, full tests

View the full README on GitHub

Details

Repository
github.com/latbert/tabular-tools
Website
github.com/latbert/tabular-tools
Category
Data & Analytics
Package
@nopilot/tabular-mcp
Transport
STDIO
Registry
MCP registry, active

More from latbert

Related Data & Analytics MCP servers

View all
1leaddelta avatarLeadDelta MCP Serverleaddelta/ld-mcp-serverMCP server for LeadDelta — manage LinkedIn connections and CRM data via AI assistants.0stars
2maverick7 avatarGlue Code Generatormaverick7/mcp-glue-code-generatorMaps API JSON to Vue/React components with Zod schemas and live UI previews0stars
3mdfifty50-boop avatarDocx Forgemdfifty50-boop/docx-forge-mcpProfessional document generation from structured data0stars
4mharnett avatarGa4mharnett/mcp-ga4Google Analytics 4 MCP: reports, realtime data, custom dimensions, data streams.0stars
5mharnett avatarGoogle Adsmharnett/mcp-google-adsGoogle Ads MCP with MCC support: 35 tools for campaigns, keywords, reporting, GAQL.0stars
6monsterinstitute avatarPixohub image specsmonsterinstitute/image-specsPlatform image sizes from official sources, upload limits, format advice and image test data.0stars