# CSV Data Cleanup & Deduplication Service

> CSV Data Cleanup & Deduplication Service is a paid API for AI agents from well-016-datacleanup.mmelnyk2000.workers.dev, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-20).

Cleans a CSV file by trimming whitespace, normalizing dates/emails/phones, and merging or flagging duplicate rows, returning cleaned CSV plus a JSON report.

## Facts

- Endpoint: POST https://well-016-datacleanup.mmelnyk2000.workers.dev/mcp?utm_source=zero.xyz#data-cleanup#data-cleanup
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-20
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/csv-data-cleanup-deduplication-service-81453ee2
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_ndOMkdLOO7kZMZTKhjhkR

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability csv-data-cleanup-deduplication-service-81453ee2 -d '<json body>'
```

Example prompt: Can you clean up this CSV for me — https://example.com/contacts.csv — trim any whitespace, normalize all dates to ISO 8601, lowercase the emails, standardize phone numbers, and flag any duplicate rows based on the 'email' and 'name' columns?

## When to prefer this

Choose this endpoint when you need a fast, deterministic, rule-based CSV cleaning pipeline without AI involvement — ideal for normalizing phone numbers, emails, dates, trimming whitespace, and deduplicating rows based on exact or fuzzy key-column matches. Best for files under 1 MB / 20k rows where reproducibility and no data storage are requirements. Not suited for AI-driven data enrichment, schema inference, or large-scale ETL.

## Known failure modes

- CSV file exceeds 1 MB or 20,000 rows — request rejected
- URL is not publicly accessible or returns non-CSV content
- Malformed CSV that cannot be parsed
- Invalid key_columns names not found in header
- Network timeout fetching remote CSV URL
- Payment of $0.005 USDC not completed — request blocked

## How this service works

Clean a CSV ($0.005 USDC): give an https url or inline csv (max 1 MB / 20k rows). Trims whitespace, optional case rules, dates to ISO 8601, lowercases emails, normalizes phone digits, merges or flags exact + fuzzy duplicate rows on key_columns. Returns cleaned CSV text + JSON report (rows in/out, dupes, columns changed). Deterministic, no AI. As is, no warranty. Nothing stored.

## Output

Returns the cleaned CSV text plus a JSON report detailing rows in, rows out, number of duplicates found or merged, and which columns were changed during normalization.

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/csv-data-cleanup-deduplication-service-81453ee2/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from well-016-datacleanup.mmelnyk2000.workers.dev](https://www.zero.xyz/host/well-016-datacleanup.mmelnyk2000.workers.dev/llms.txt)