Data Profiler runs on your own machine — the client starts it, so there is no endpoint to ping. 112 installs a week from pypi. Last commit 8 Aug 2026.
Profile local CSV, Parquet, JSON and Excel files into a compact data-quality summary.
Today is the operative word: we check Data Profiler every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add mcp-data-profiler -- uvx mcp-data-profiler
{
"mcpServers": {
"mcp-data-profiler": {
"args": [
"mcp-data-profiler"
],
"command": "uvx"
}
}
}
[mcp_servers.mcp-data-profiler]
command = "uvx"
args = ["mcp-data-profiler"]
{
"mcpServers": {
"mcp-data-profiler": {
"args": [
"mcp-data-profiler"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"mcp-data-profiler": {
"args": [
"mcp-data-profiler"
],
"command": "uvx"
}
}
}
Profiles CSV/Parquet/Excel/JSON files: schema, stats, quality flags and dtype tips for LLM agents.
Create interactive visualizations and query data sources (SQLite, CSV, Parquet, JSON)
Local CSV, JSON and Excel conversion. Files are never uploaded and never enter the context.
Read-only WHOOP v2 data for MCP clients, with local SQLite cache and CSV/JSONL/Parquet exports.
Offline MCP server to explore CSV/JSON/Parquet/Excel: preview, query, diff, render interactive HTML
Query a folder of CSV / Parquet / JSON files with SQL — one queryable source, read-only.
Query, join, profile, clean and convert CSV/JSON/Parquet with server-side DuckDB over MCP.
Standardize, reshape, and normalize messy data — CSV, Excel, Parquet, S3, databases.
Answers built from our own checks of this server.