Frenchie
MCP loadingLog inDashboard

csv extraction

Turn CSV exports into Markdown tables.

CSV is simple until your agent has to reason over it. Frenchie handles quoting, headers, truncation, and output shape so the agent gets a clean table.

Install the skill packRead docs →
$Extract ./customers.csv to Markdown with Frenchie

✓ extracted · saved → result.md

# Extracted Markdown

## Sheet: Summary

| Field | Value |
| ----- | ----- |
| ARR   | $4.9M |
| Risk  | Procurement delay |

## Notes

- Source file preserved as
  agent-readable Markdown.
- Your agent does the reasoning
  after extraction.

why it exists

Files first. Reasoning after.

Raw CSV in a prompt is brittle. Quoted commas, long rows, missing headers, and oversized exports make the agent spend attention on parsing instead of the work you asked for.

Frenchie parses CSV with standard quoting rules and returns agent-friendly Markdown tables. Large files may be chunked, so truncation notes can appear per chunk instead of as one global row count.

quick start

Install skills and MCP tools together.

The installer configures the MCP server and installs the Frenchie skills alongside the MCP tools, so your agent has the callable tools and the instructions for when to use them.

01

Install Frenchie

$ npx @lab94/frenchie install --api-key fr_...

This writes the local stdio MCP config and copies the Frenchie skills into your project.

02

Ask your agent to extract

> Extract ./customers.csv to Markdown with Frenchie

Your agent calls extract_to_markdown. Stdio results auto-save to .frenchie/<name>/result.md.

03

Reason over Markdown

CSV extraction costs 0.5 credit per file. CSV files can be up to 20 MB. Results expire 30 minutes after first delivery.

workflow

How it runs.

  1. 1

    Install Frenchie with MCP tools and skills together.

  2. 2

    Ask your agent to extract the CSV export.

  3. 3

    Frenchie parses the file and returns a Markdown table.

  4. 4

    Your agent can clean columns, flag anomalies, or draft a report from the table.

questions

The practical bits.

Does Frenchie render every CSV row?

No. It keeps the Markdown agent-friendly. Large CSV files may be processed in chunks, with row samples and truncation notes emitted per chunk.

Does it support quoted commas?

Yes. CSV parsing follows standard quoting and escaping rules.

Should I use this for million-row analytics?

No. Use a database or warehouse for that. Frenchie is for agent-readable extraction, not large-scale analytics.

Give your agent a real file.

Install Frenchie, drop in a DOCX, XLSX, CSV, TSV, or PPTX file, and see the Markdown your agent gets back.

Install the skill packBrowse use cases →