About DataClean
DataClean is an MCP server for preparing CSV, Excel and JSON tables for data analysis and AI agents. It profiles, cleans and validates data with deterministic rules, preserving and flagging values whose meaning is ambiguous rather than guessing.
Key features
- 01Profile columns and detect data issues
- 02Clean and export typed tables
- 03Validate rows against schemas
- 04Normalize lists of common values
- 05Preserve ambiguous values and flag them
- 06Protect spreadsheet exports from formulas
Use cases
- 01Inspect a table before analysis
- 02Standardize dates and numbers in imports
- 03Check records against required fields
- 04Prepare clean data from CSV or Excel
MCP support
Exposes table profiling, cleaning, schema validation and value normalization tools to MCP clients.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mcp.keyflint.dev/dataclean/mcpclaude mcp add --transport http arceedev-dataclean https://mcp.keyflint.dev/dataclean/mcp{"mcpServers":{"arceedev-dataclean":{"type":"http","url":"https://mcp.keyflint.dev/dataclean/mcp"}}}Open in Cursor{"servers":{"arceedev-dataclean":{"type":"http","url":"https://mcp.keyflint.dev/dataclean/mcp"}}}Open in VS Code{"mcpServers":{"arceedev-dataclean":{"type":"http","url":"https://mcp.keyflint.dev/dataclean/mcp"}}}{"mcpServers":{"arceedev-dataclean":{"serverUrl":"https://mcp.keyflint.dev/dataclean/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMEdataclean-mcp
An MCP server that cleans tables deterministically before an AI agent reasons over them. LLMs misread 1.250,50 €, swap day and month in 03/04/2026, choke on NUL bytes and mojibake (Café), and silently drop leading zeros. DataClean fixes these with rules, and it never guesses: an ambiguous value is kept as it was and flagged, and it is converted only when the rest of its column (or a parameter you pass) settles its meaning.
| Tool | Credits | What it does |
|---|---|---|
profile_table | 1 | Encoding, delimiter, header row, and for each column: real type (integer, decimal, date, datetime, boolean, email, url, phone, iban, text), number locale, date order, currency, nulls, distinct values, min/max, examples and problems. Also reports duplicate rows and a suggested schema. |
clean_table | 1 | Returns a clean, typed copy as CSV, TSV, JSON, JSONL or typed .xlsx: text trimmed and repaired, numbers as plain decimals, dates in ISO 8601, phones in E.164, IBANs compacted, rows deduplicated, headers made unique or snake_case. Every value left unconverted is listed with its source row. |
validate_schema | 1 | Checks every row against a schema (type, required, unique, min/max, min_length/max_length, enum, pattern) and returns errors with their row numbers. |
normalize_values | 1 | Normalizes a list of up to 10,000 values (amounts, dates, phones, emails…) taken from a document or another tool. |
pricing, credits_balance | 0 | Free helpers. |
Charging works like this:
- Unreadable input or invalid parameters are refused before any credits are charged.
- A failure after charging is refunded.
What it fixes
- Numbers:
1.250,50 €,$1,250.50,1 234,5,1'234.50,(45.30), SAP-style1.250,50-,12,5 %,EUR 12. The column decides whether a value like1,250uses a thousands or a decimal separator. If nothing in the column decides it,number_localedoes, and without either the value is flaggedambiguous_number. - Dates: ISO,
13/04/2026(day-first),04/13/2026(month-first),5 de marzo de 2026,March 5, 2026,5-Mar-26,3. März 2026, and times with am/pm.03/04/2026is converted only when another value in the column, ordate_order, settles the order. Dates in the minority order are flaggeddate_order_conflict. - Text: removes NUL, control and zero-width characters, turns NBSP into a normal space, repairs mojibake, applies Unicode NFC, and collapses and trims spaces. Null markers (
NULL,N/A,#N/A,-,nan…) become empty. - IDs: digit strings with leading zeros or more than 15 digits (zip codes, card numbers, references) stay text and are never turned into numbers.
- Files: CSV in UTF-8, UTF-16 or Windows-1252, delimiter detected automatically (
, ; tab |), title rows above the header skipped, ragged rows padded, duplicate or empty headers renamed. Also reads.xlsx(via base64) and JSON/JSONL. - Safety: in CSV output, text cells starting with
= + - @get a'prefix so spreadsheets do not run them as formulas. In.xlsxoutput they are stored as strings. Schema regexes with nested quantifiers are refused (ReDoS).
Install
- Buy credits at https://mcp.keyflint.dev to get a license (
LIC-...). - Add the server to your client:
{
"mcpServers": {
"dataclean": {
"command": "uvx",
"args": ["dataclean-mcp"],
"env": { "KEYFLINT_LICENSE": "LIC-..." }
}
}
}
Claude Desktop also installs the .mcpb bundle attached to each GitHub release. Hosted mode runs dataclean-mcp --http (or uses the Dockerfile) and reads the license from each request's Authorization: Bearer LIC-... header.
Limits (set by environment variables): DATACLEAN_MAX_BYTES (20 MB), DATACLEAN_MAX_ROWS (200,000), DATACLEAN_MAX_OUTPUT (15 MB). Credit prices can be overridden with DATACLEAN_PRICES=clean_table=2,....
Visual cards (MCP Apps)
In Claude, ChatGPT, VS Code and Goose every paid tool and credits_balance renders as an interactive card in the
chat: credit balance with a refill bar and a buy button, or a result summary (key figures, issues, table preview and
credits charged). It is the ui://dataclean/card.html resource, self-contained with no network access. Other clients
keep getting the same JSON as before.
Tests
pip install -e '.[test]'
pytest -q
The tests use a fake KeyFlint gateway and locally signed licenses, so they need no network.
License
Business Source License 1.1. Production use requires a KeyFlint license from the Licensor. On 2030-11-05 the code becomes Apache 2.0.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.