# jDataMunch MCP

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.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 82
- Author: jgravelle
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/jgravelle/jdatamunch-mcp
- Updated: 2026-10-21
- HTML: https://affpapa.org/en/nevibecode/mcp/jdatamunch-mcp

## What it 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.

## Requirements
- Needs: Python and uv (commands run via uvx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add jdatamunch-mcp -- uvx jdatamunch-mcp
```
uvx runs the command named after the package; if the README names another one, use uvx --from jdatamunch-mcp <command>

### Codex

**Platform CLI**
```bash
codex mcp add jdatamunch-mcp -- uvx jdatamunch-mcp
```
uvx runs the command named after the package; if the README names another one, use uvx --from jdatamunch-mcp <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "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>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "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>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add jdatamunch-mcp uvx jdatamunch-mcp
```
uvx runs the command named after the package; if the README names another one, use uvx --from jdatamunch-mcp <command>

## When to use it
- 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
- 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

## Similar
- [World Monitor](https://affpapa.org/en/nevibecode/mcp/world-monitor.md) — MCP server · ★ 89408
- [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89433
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16717
- [PostHog MCP Server](https://affpapa.org/en/nevibecode/mcp/posthog-mcp-server.md) — MCP server · ★ 40409
- [dbx](https://affpapa.org/en/nevibecode/mcp/dbx.md) — MCP server · ★ 27669
- [Metabase](https://affpapa.org/en/nevibecode/mcp/metabase.md) — MCP server · ★ 49845

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md