# DataClean (pypi · dataclean-mcp)

Profile, clean and validate CSV/Excel data: schemas, dates, numbers, duplicates. Never guesses.

- Trust score: 66/100 (medium)
- Change this week: −8
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `mcp.keyflint.dev`: 32/100, [markdown](https://verifymcp.io/servers/arceedev-dataclean-mcp/dataclean-mcp.md), [page](https://verifymcp.io/servers/arceedev-dataclean-mcp/dataclean-mcp)
- pypi · `dataclean-mcp`: 66/100 (this document), [markdown](https://verifymcp.io/servers/arceedev-dataclean-mcp/dataclean-mcp-2.md), [page](https://verifymcp.io/servers/arceedev-dataclean-mcp/dataclean-mcp-2)

## Channel facts

- Registry: `pypi`
- Package: `dataclean-mcp`
- Version: `0.2.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Supply Chain Security**: 49/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it.
  - 3 of 31 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 84/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to ArceeDev/dataclean-mcp).
  - License check failed: the license (BUSL-1.1) isn't a recognized OSI-approved license.
  - Actively maintained (last published 5 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 66/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2337 tokens (~333/item across 7 items; 6 tools + 1 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 50/100
  - Stability observed for 15 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).
  - Supports UI / widget rendering.

## Install

### How do I install the DataClean MCP server?

DataClean runs locally as a PyPI package, launched with uvx dataclean-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add arceedev-dataclean-mcp -- uvx dataclean-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "arceedev-dataclean-mcp": {
      "command": "uvx",
      "args": [
        "dataclean-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "arceedev-dataclean-mcp": {
      "command": "uvx",
      "args": [
        "dataclean-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add arceedev-dataclean-mcp -- uvx dataclean-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "arceedev-dataclean-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "dataclean-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add arceedev-dataclean-mcp --command uvx --arg dataclean-mcp
```

### Hermes

```yaml
mcp_servers:
  arceedev-dataclean-mcp:
    command: "uvx"
    args: ["dataclean-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "arceedev-dataclean-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "dataclean-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add arceedev-dataclean-mcp -t stdio -c uvx -a dataclean-mcp
```

### Other

```json
{
  "mcpServers": {
    "arceedev-dataclean-mcp": {
      "command": "uvx",
      "args": [
        "dataclean-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-21 (score 66, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-20 (score 81, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-11-18 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-17 (score 64, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-16 (score 79, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-11-15 (score 63, −11)

- [security regression] Malware scan: pass → unverified
- [functional improvement] Stability: unverified → 0.30
- [functional] Package version: 0.2.0 → 0.2.1

### 2026-11-12 (score 74, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-11 (score 59, −15)

- [security regression] Malware scan: pass → unverified

## MCP tools (6)

### `profile_table` (~470 tokens)

Profile table data quality

Profile a table: what each column really contains and what is wrong with it, without changing it.

Returns the detected encoding/delimiter/header, per-column type, nulls, distinct values, min/max, number
locale, date order, currency, examples and notes (leading-zero IDs, formula-injection cells, ambiguous dates
or numbers, mixed separators), table issues (ragged rows, NUL bytes, duplicate headers, title rows), exact
duplicate rows, the first 50 flagged cells and a suggested schema for validate_schema.

    Input (exactly one): content (CSV/TSV/JSON text), content_base64 (file bytes: .xlsx, or CSV in any encoding),
    rows (JSON list of objects or of lists). delimiter: auto-detected (, ; tab |). sheet: Excel sheet name (default
    the first). has_header: false when the first row is data. header_row: 1-based row of the header (default auto,
    skipping title rows above it).
    Parsing: number_locale 'eu' (1.234,56) or 'us' (1,234.56) settles values like 1,250 (auto from the column
    otherwise). date_order 'dmy' or 'mdy' settles dates like 03/04/2026 (auto from the column otherwise).
    phone_country (ISO-2, e.g. ES, US, GB) converts national phone numbers to E.164. null_values: extra strings
    read as empty (NULL, N/A, -, #N/A and similar are already). types: force a type per column, e.g.
    {"zip": "text", "amount": "decimal"}; types are text, integer, decimal, boolean, date, datetime, email, url,
    phone, iban.

Input parameters:

- `content` (string)
- `content_base64` (string)
- `date_order` (string)
- `delimiter` (string)
- `has_header` (boolean)
- `header_row` (integer)
- `null_values`
- `number_locale` (string)
- `phone_country` (string)
- `rows`
- `sheet` (string)
- `types`

### `clean_table` (~733 tokens)

Clean and standardize table

Return a clean, typed copy of a table, with a report of every change and every value left unconverted.

Text: NUL/control/zero-width characters removed, mojibake repaired (CafÃ© -> Café), Unicode NFC, spaces
collapsed and trimmed. Numbers: plain decimals (1.250,50 € -> 1250.50; (45) -> -45; 1.250,50- -> -1250.50).
Dates: ISO 8601. Booleans: true/false. Emails: domain lowercased. Phones: E.164. IBAN: compact uppercase.
Values that do not fit the column type are kept as they were (on_invalid='null' empties them) and listed
in `flags` with their source row.

Args:
    output_format: csv (default) | tsv | json | jsonl | xlsx (typed cells; returned only as content_base64).
    header_style: keep | snake (Fecha de alta -> fecha_de_alta). columns: keep only these columns, in order.
    dedupe: none | exact | ignore_case, over all columns or `dedupe_keys`; the first occurrence is kept.
    drop_empty_columns: remove columns with no values. output_delimiter: for csv output.
    formula_guard: prefix text cells starting with = + - @ with ' in CSV so spreadsheets do not run them.

    Input (exactly one): content (CSV/TSV/JSON text), content_base64 (file bytes: .xlsx, or CSV in any encoding),
    rows (JSON list of objects or of lists). delimiter: auto-detected (, ; tab |). sheet: Excel sheet name (default
    the first). has_header: false when the first row is data. header_row: 1-based row of the header (default auto,
    skipping title rows above it).
    Parsing: number_locale 'eu' (1.234,56) or 'us' (1,234.56) settles values like 1,250 (auto from the column
    otherwise). date_order 'dmy' or 'mdy' settles dates like 03/04/2026 (auto from the column otherwise).
    phone_country (ISO-2, e.g. ES, US, GB) converts national phone numbers to E.164. null_values: extra strings
    read as empty (NULL, N/A, -, #N/A and similar are already). types: force a type per column, e.g.
    {"zip": "text", "amount": "decimal"}; types are text, integer, decimal, boolean, date, datetime, em…

Input parameters:

- `columns`
- `content` (string)
- `content_base64` (string)
- `date_order` (string)
- `dedupe` (string)
- `dedupe_keys`
- `delimiter` (string)
- `drop_empty_columns` (boolean)
- `fix_mojibake` (boolean)
- `formula_guard` (boolean)
- `has_header` (boolean)
- `header_row` (integer)
- `header_style` (string)
- `null_values`
- `number_locale` (string)
- `on_invalid` (string)
- `output_delimiter` (string)
- `output_format` (string)
- `phone_country` (string)
- `rows`
- `sheet` (string)
- `types`

### `validate_schema` (~615 tokens)

Validate table against schema

Check every row of a table against a schema, after the same parsing clean_table applies.

schema: {"columns": {"id": {"type": "integer", "required": true, "unique": true},
                     "email": {"type": "email", "required": true},
                     "amount": {"type": "decimal", "min": 0, "max": 100000},
                     "signup": {"type": "date", "min": "2020-01-01"},
                     "status": {"enum": ["active", "churned"]},
                     "sku": {"type": "text", "pattern": "[A-Z]{3}-\\d{4}", "max_length": 8}},
         "strict_columns": false}
Rules: type, required, unique (case-insensitive), min/max (numbers and dates), min_length/max_length, enum
(case-insensitive), pattern (full match; nested quantifiers are refused). Column names match case-insensitively.
strict_columns flags columns that are not in the schema. Errors carry the source row number; `valid` is
true only with zero errors. profile_table returns a suggested schema to start from.

    Input (exactly one): content (CSV/TSV/JSON text), content_base64 (file bytes: .xlsx, or CSV in any encoding),
    rows (JSON list of objects or of lists). delimiter: auto-detected (, ; tab |). sheet: Excel sheet name (default
    the first). has_header: false when the first row is data. header_row: 1-based row of the header (default auto,
    skipping title rows above it).
    Parsing: number_locale 'eu' (1.234,56) or 'us' (1,234.56) settles values like 1,250 (auto from the column
    otherwise). date_order 'dmy' or 'mdy' settles dates like 03/04/2026 (auto from the column otherwise).
    phone_country (ISO-2, e.g. ES, US, GB) converts national phone numbers to E.164. null_values: extra strings
    read as empty (NULL, N/A, -, #N/A and similar are already). types: force a type per column, e.g.
    {"zip": "text", "amount": "decimal"}; types are text, integer, decimal, boolean, date, datetime, email, url,
    phone, iban.

Input parameters:

- `content` (string)
- `content_base64` (string)
- `date_order` (string)
- `delimiter` (string)
- `has_header` (boolean)
- `header_row` (integer)
- `max_errors` (integer)
- `null_values`
- `number_locale` (string)
- `phone_country` (string)
- `rows`
- `schema` (object, required)
- `sheet` (string)

### `normalize_values` (~185 tokens)

Normalize values

Normalize a list of up to 10,000 values of one kind, e.g. amounts, dates or phone numbers from a document.

kind: auto (inferred like a table column) | number | integer | decimal | date | datetime | boolean | email |
url | phone | iban | text. name: optional column name, used as a hint (e.g. 'phone', 'fecha').
Returns one result per input, in order: {"input", "output", "valid"} and "reason" when it could not be
converted. Output types: numbers as plain decimal strings, dates ISO 8601, phones E.164.

Input parameters:

- `date_order` (string)
- `kind` (string)
- `name` (string)
- `number_locale` (string)
- `phone_country` (string)
- `values` (array, required)

### `pricing` (~20 tokens)

Show tool prices

Credit price of each tool and where to buy credits. Free.

### `credits_balance` (~19 tokens)

Check credit balance

Remaining credits on your KeyFlint license. Free.

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/arceedev-dataclean-mcp/dataclean-mcp-2#diagnostics

## Score history

- 2026-11-21: 66
- 2026-11-20: 81
- 2026-11-19: 65
- 2026-11-18: 65
- 2026-11-17: 64
- 2026-11-16: 79
- 2026-11-15: 63
- 2026-11-14: 74
- 2026-11-13: 74
- 2026-11-12: 74
- 2026-11-11: 59
- 2026-11-10: 74
- 2026-11-09: 74
- 2026-11-08: 74
- 2026-11-07: 74
- 2026-11-06: 59

## Common questions

### What is the DataClean MCP server?

DataClean is an MCP server listed in the public MCP registry as io.github.ArceeDev/dataclean-mcp. Profile, clean and validate CSV/Excel data: schemas, dates, numbers, duplicates. Never guesses. This page covers its PyPI package (dataclean-mcp).

### Is the DataClean MCP server safe to use?

DataClean scores 66 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the DataClean MCP server expose?

DataClean exposes 6 tools: profile_table, clean_table, validate_schema, normalize_values, pricing, credits_balance. Their descriptions and schemas cost roughly 2,042 tokens of context every time the server is loaded.

### Is the DataClean MCP server still maintained?

DataClean is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the DataClean MCP server under?

DataClean declares the BUSL-1.1 licence, which is not on the OSI-approved list. Read the terms before using it at work, and note this covers the source only, not the cost of any service it calls.

### What did VerifyMCP test on the DataClean MCP server?

VerifyMCP ran 16 checks on DataClean, covering Known CVEs, Install scripts, Dependency health, Source repository and 12 more. One item could not be completed, a gap on our side rather than a finding about DataClean: Malware scan. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- PyPI project: https://pypi.org/project/dataclean-mcp/
- Socket report: https://socket.dev/pypi/package/dataclean-mcp
- Repository: https://github.com/ArceeDev/dataclean-mcp
- Website: https://mcp.keyflint.dev/
- Changelog RSS feed: https://verifymcp.io/servers/arceedev-dataclean-mcp/dataclean-mcp-2.xml
- Changelog JSON feed: https://verifymcp.io/servers/arceedev-dataclean-mcp/dataclean-mcp-2/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/arceedev-dataclean-mcp/dataclean-mcp-2.json
- HTML version of this page: https://verifymcp.io/servers/arceedev-dataclean-mcp/dataclean-mcp-2
