jDataMunch MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 614 installs a week from pypi. Last commit 21 Oct 2026.
Tabular data retrieval. Index CSV/Excel, query rows, aggregate. 99%+ savings vs raw file reads.
Today is the operative word: we check jDataMunch MCP 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 jdatamunch-mcp -- uvx jdatamunch-mcp
{
"mcpServers": {
"jdatamunch-mcp": {
"command": "uvx",
"args": [
"jdatamunch-mcp"
]
}
}
}
[mcp_servers.jdatamunch-mcp]
command = "uvx"
args = ["jdatamunch-mcp"]
{
"mcpServers": {
"jdatamunch-mcp": {
"command": "uvx",
"args": [
"jdatamunch-mcp"
]
}
}
}
{
"servers": {
"jdatamunch-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"jdatamunch-mcp"
]
}
}
}
Local data runtime for AI agents: query CSV, Excel, Parquet and JSON files with DuckDB SQL.
Profile local CSV, Parquet, JSON and Excel files into a compact data-quality summary.
Tabular data for AI agents — load CSV/JSON/XLSX, query, group-by, stats (no database).
Offline MCP server to explore CSV/JSON/Parquet/Excel: preview, query, diff, render interactive HTML
Excel automation for AI - Sheets, Power Query, DAX, VBA, Tables, Ranges and more. Windows only.
Returns rows of any Apify dataset, CSV/Excel/JSON file URL or Google Sheet that pass filter...
Query Yandex Metrica analytics — reports, trends, metadata and raw log exports — via an AI agent.
Kibana/Elasticsearch MCP — log search, aggregations, index discovery, dashboards.
Answers built from our own checks of this server.