# Data Cleaner Muse connector

From musedirectory.ai, the independent directory of Meta Muse connectors. Not affiliated with Meta.

## Data Cleaner

Turns messy CSV, Excel, JSON or XML files into clean tables you can query and export.

- Record: https://musedirectory.ai/connector/data-cleaner
- Category: Research & Data
- Developer: data-cleaner.com (https://data-cleaner.com/mcp/)
- Muse status: Extra setup. Not in Muse's Connectors list yet. Muse can still use it: its page gives you a request to paste into Muse.
- Health: Working, 218ms, checked 2026-11-20T13:30:44Z
- Endpoint: https://mcp.data-cleaner.com/mcp?channel=ch-0S999H2GZ0KP7
- Auth: No account needed; Pricing: unknown
- Screening: Screened, no issues found (2026-11-20T06:11:13Z)
- Source: Found in the official MCP Registry (com.data-cleaner/data-cleaner) https://registry.modelcontextprotocol.io/v0/servers?search=com.data-cleaner%2Fdata-cleaner

Connects to a file at a URL or one you upload, and cleans it into a typed table: handles odd encodings, banner rows, merged cells, thousands separators and mixed date formats. Muse can then filter, join and run SQL over the table and export the result as CSV, Excel, JSON or Parquet.

Example request: "Clean up this supplier price list I downloaded and show me the average unit cost by category."

How to connect: Not in Muse's Connectors list yet, but Muse can still use it. Paste this into Muse: "Use Data Cleaner to help me. It is a free service with an MCP server at https://mcp.data-cleaner.com/mcp?channel=ch-0S999H2GZ0KP7. It does not need an API key. Ask me before you share anything with it." Muse asks before it shares anything with the app's site. Meta does not review apps used this way, so only use ones you trust. We tested this in the Muse app on September 24, 2026: Muse used an app's link directly this way and returned a live answer.

Tools:
- fetch: Load a table from a URL (or reopen one by its table_id) and get back a clean, typed table. Reads CSV, Excel (.xls/.xlsx), JSON, XML, SDMX, Parquet, Stata, fixed-width or zipped files, including messy ones (unknown encoding, banner rows, merged cells, thousands separators, dates i
- describe: Describe a table without reading its rows: the typed schema (schema_columns and the bare column names), the total row_count and when the table_id expires. A cheap call to check that a table_id still works, to plan a query or a join, or to size a table before paging it. A table_id
- rows: Page through the rows of a table: a table_id from fetch, upload_confirm, wrangle or sql_query. Returns rows page*page_size .. (page+1)*page_size-1, the total row_count and has_more (false on the last page). Nothing is downloaded or cleaned again: only the requested slice is read.
- wrangle: Run one operation on a table and get back a NEW scratch table: preview rows, `result_row_count` (the number of rows IN THE RESULT, not an answer: an aggregate returns one row and its number is the value in `preview`) and its own table_id. The source table is never modified. The o
- sql_query: Run one SELECT statement over a table and get back a NEW scratch table with its own table_id -- the SQL surface of `wrangle` (GROUP BY, JOIN, window functions, CAST). `dialect` names the SQL dialect: duckdb, postgres, sparksql or mysql (transpiled). The primary table is `t`. A jo
- export: Get a DOWNLOAD LINK for a table, as a file: csv, xlsx (Excel), json or parquet -- the whole table, not a page of it: a cleaned table, or a wrangle / sql_query result. The `download_url` opens in a browser or with curl and needs no key. The link works for ONE HOUR, then stops; a n
- upload_request: Open an upload slot for a FILE OF THE USER'S -- one on their computer or phone, or one attached to the chat. A file reaches this service only through the slot: a chat attachment lives in a sandbox with no connection to this service, and file bytes retyped or base64'd into a tool 
- upload_confirm: Finish an upload: once the file is on the `upload_page` (or a shell PUT it), this cleans it into a private scratch table -- the same clean, typed result as fetch. Returns the table_id and when it expires, the schema, row count, issues and a page of rows. The file's own name is kn

Screening checks:
- MCP handshake: pass (Answered in 940ms)
- Domain against threat feeds (Cloudflare security DNS): pass (mcp.data-cleaner.com, data-cleaner.com not flagged)
- Published packages against the OSV malicious-package database: n/a (No npm or PyPI package published)
- Hidden instructions or invisible characters in tool text: pass (8 tools read, nothing found)
- Inputs asking for passwords, card numbers or seed phrases: pass (None found)
- Domain and redirects: pass (Domain registered 933 days ago)
- AI review of purpose and tool behavior: pass (No concerns)
