jDataMunch MCP — Claude Code MCP server: features and install
Local tabular retrieval for CSV, Excel, Parquet, and JSONL without dumping millions of raw rows into LLM context. It aggregates and filters datasets on your machine.
claude mcp add jdatamunch-mcp -- uvx jdatamunch-mcpWhat jDataMunch MCP does
The server runs over stdio to query tabular files locally. It profiles files once, recording column types and missing value counts. Queries run directly against the local data. The model gets only matching rows.
Agents receive 39 specialized tools. They handle local SQL runs and detect possible joins between datasets. Loading Excel or Parquet files requires extra dependencies at launch. Python 3.10+ is strictly required.
What it helps with
- query large CSV tables without context bloat
- run grouping and aggregation operations server-side
- inspect missing values in dataset columns locally
- detect join keys across separate data files
Example prompts for the agent
- Use jdatamunch to index ./data/sales.csv and show the schema
- Check which columns have null values in the sales dataset and count rows by status
How to install jDataMunch MCP
Platform CLI
claude mcp add jdatamunch-mcp -- uvx jdatamunch-mcpuvx runs the command named after the package; if the README names another one, use uvx --from jdatamunch-mcp <command>
Platform CLI
codex mcp add jdatamunch-mcp -- uvx jdatamunch-mcpuvx runs the command named after the package; if the README names another one, use uvx --from jdatamunch-mcp <command>
Config file
{
"mcpServers": {
"jdatamunch-mcp": {
"command": "uvx",
"args": [
"jdatamunch-mcp"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from jdatamunch-mcp <command>
Config file
{
"servers": {
"jdatamunch-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"jdatamunch-mcp"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from jdatamunch-mcp <command>
Platform CLI
gemini mcp add jdatamunch-mcp uvx jdatamunch-mcpuvx runs the command named after the package; if the README names another one, use uvx --from jdatamunch-mcp <command>
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about jDataMunch MCP
How to install jDataMunch MCP in Claude Code?
Run claude mcp add jdatamunch-mcp -- uvx jdatamunch-mcp in your terminal. The server requires Python 3.10 or newer.
What does jDataMunch MCP do?
It queries tabular files on your machine and sends back only matching rows or aggregations. Raw files never enter the conversation context.
How do you query Excel and Parquet formats?
Supply --from "jdatamunch-mcp[excel,parquet]" when adding the server with uvx. Without these extras, the package handles plain CSV and JSONL files.
