Skip to main content
Glama
Claude MCP Data Explorer

Claude MCP Data Explorer

by tofunori

Claude MCP Data Explorer for Windows

A TypeScript implementation of a Model Context Protocol (MCP) server for data exploration with Claude. This server integrates with Claude Desktop and enables advanced data analysis by providing tools to load CSV files and execute JavaScript data analysis scripts.

Prerequisites

Related MCP server: mcp-csv-analyst

Installation (Updated for Windows)

  1. Clone this repository

    git clone https://github.com/tofunori/claude-mcp-data-explorer.git
    cd claude-mcp-data-explorer
  2. Install dependencies

    npm install
  3. Build and run setup script

    npm run setup

    This will:

    • Build the TypeScript code to JavaScript

    • Configure Claude Desktop to use the compiled JavaScript

    • Create necessary directories

  4. Restart Claude Desktop and enable Developer Mode

    • Close Claude Desktop completely

    • Start Claude Desktop

    • Go to Help → Enable Developer Mode

Manual Testing

You can test the server directly by running:

npm run build
npm run start

The server should start without errors. If you can run this successfully, Claude Desktop should be able to use the server as well.

How It Works

This MCP server provides two main tools for Claude:

  1. load-csv - Loads CSV data into memory for analysis

  2. run-script - Executes JavaScript code for data processing and analysis

It also includes a prompt template that guides Claude through a structured data exploration process.

Usage

  1. Start Claude Desktop

  2. Select the "Explore Data" prompt template

    • This prompt will appear in Claude Desktop after setup

  3. Enter CSV file path and exploration topic

    • Example file path: C:/Users/YourName/Documents/data.csv

    • Example topic: "Sales trends by region"

  4. Let Claude analyze your data

    • Claude will load the CSV file and generate insights automatically

    • The server handles large files efficiently using chunking

Troubleshooting

  1. Claude doesn't show the MCP server

    • Check the configuration file at %APPDATA%\Claude\claude_desktop_config.json

    • It should point to the compiled JavaScript file in the dist directory

    • Try rebuilding the project with npm run build

    • Enable Developer Mode and check the MCP Log File (Developer → Open MCP Log File)

    • Use Developer → Reload All MCP Servers to force refresh

  2. Permission errors reading files

    • Make sure Claude has access to the CSV file location

    • Try using absolute paths with forward slashes (/) or escaped backslashes (\\)

  3. JavaScript errors in scripts

    • Check that your script is compatible with the allowed modules

    • Review any error messages in Claude's response

License

MIT License - see LICENSE file for details.

Acknowledgments

  • Based on the official MCP TypeScript SDK from Anthropic

  • Thanks to the MCP community for examples and inspiration

Available Tools

2 tools
load-csvC

Load a CSV file into a DataFrame for analysis

Inputs: csv_path (required), df_name.

run-scriptC

Execute a JavaScript script for data analysis and visualization

Inputs: script (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3/5.0

    Scored across 2 tools

    Disambiguation5/5

    The two tools have clearly distinct purposes: one loads CSV data into a DataFrame, while the other executes JavaScript scripts for analysis and visualization. There is no overlap or ambiguity between these functions, making it easy for an agent to select the correct tool.

    Naming Consistency4/5

    Both tools use a verb-noun pattern (load-csv, run-script), which is consistent and readable. The hyphenated style is maintained throughout, though the specific convention (hyphens vs. underscores) is less important than the consistency, which is good here with only minor deviations from common patterns.

    Tool Count2/5

    With only two tools, the server feels thin for a 'Data Explorer' purpose, as it lacks essential operations like data querying, filtering, transformation, or exporting. While the tools are functional, the count is too low to adequately cover the expected scope of data exploration and analysis.

    Completeness2/5

    For a data exploration server, there are significant gaps: no tools for querying data, filtering, aggregating, visualizing beyond scripts, or exporting results. The surface is severely incomplete, as agents cannot perform basic data exploration tasks without relying heavily on external scripts, leading to potential failures in common workflows.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      Not graded
      maintenance
      An MCP server that enables AI assistants to load, query, and analyze local CSV files using tools for filtering, aggregation, and grouping. It provides capabilities to describe schemas, calculate statistics, and sample data directly from CSV files.
      6
      -
    • F
      license
      Not graded
      quality
      D
      maintenance
      A local MCP server for analyzing CSV files from your filesystem, particularly suited for chatbot conversation logs. Allows listing, reading, filtering, merging, and statistical analysis of CSV data via natural language.
      -
    • F
      license
      A
      quality
      D
      maintenance
      An MCP server for dataset exploration and analysis, enabling LLM clients to perform summary, correlation, distribution, missing value analysis, data cleaning, and statistical tests directly on CSV files.
      3
      -