
tabular-mcp
CSV/JSONL/xlsx toolkit: schema inference, dirty-row reports, format conversion, seeded sampling
- tools
- 3
- transport
- STDIO
- last updated
- Nov 16, 2026
Tools
3 toolsPublic 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 servers | tabular-mcp | |
|---|---|---|
| Where your data goes | uploaded to their gateway | never leaves the process |
| Works offline | no | yes |
| Extra accounts / API keys | usually yes | none |
| Deterministic output | not guaranteed | byte-identical (seeded sampling) |
| Source available | mostly closed | MIT, full tests |
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