MCPgee
MCPgee
MCPgeeMCPgee

Quick Data

v1.0.0•Data Science & ML•stable

Prompt focused MCP Server for .json and .csv agentic data analytics for Claude Code

quick-datamcpai-integration
Share:
149
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Quick Data?

Quick Data is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to prompt focused mcp server for .json and .csv agentic data analytics for claude code

Prompt focused MCP Server for .json and .csv agentic data analytics for Claude Code

This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Prompt focused MCP Server for .json and .csv agentic data an

Use Cases

Prompt focused MCP Server for .json and .csv agentic data analytics for Claude C
disler

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedApr 8, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx quick-data

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Quick Data

Quick Data MCP Server is a prompt-focused analytics engine that gives AI assistants the ability to load, explore, and analyze JSON and CSV datasets directly from the filesystem. It exposes 32 tools covering dataset loading, segmentation, correlation analysis, outlier detection, time-series analysis, visualization chart generation, and even custom Python execution against loaded data — all without requiring the user to write code manually. Data analysts and developers use it inside Claude Code to run ad-hoc explorations on local data files through natural language, turning any CSV or JSON file into an interactive analytics workspace.

Prerequisites

  • Python 3.10+ with uv package manager installed (https://docs.astral.sh/uv/)
  • Git to clone the repository
  • Local JSON or CSV files you want to analyze
  • An MCP client such as Claude Code or Claude Desktop
1

Clone the repository

Download the quick-data-mcp project to your local machine.

git clone https://github.com/disler/quick-data-mcp.git
cd quick-data-mcp
2

Set up the configuration file

Copy the sample MCP config and edit it with your absolute paths. The --directory argument tells the server where to look for data files.

cp .mcp.json.sample .mcp.json
# Edit .mcp.json and set the absolute path to your data directory
3

Verify uv path and test the server

Confirm uv is on your PATH, then do a quick smoke test by running the server directly. It should start without errors.

which uv
uv run python main.py
4

Add to your MCP client configuration

Register the server in your Claude Desktop or Claude Code config. Replace /absolute/path/to/quick-data-mcp with the real directory on your machine.

{
  "mcpServers": {
    "quick-data": {
      "command": "uv",
      "args": ["run", "--directory", "/absolute/path/to/quick-data-mcp", "python", "main.py"]
    }
  }
}
5

Discover available tools and prompts

Once connected in Claude Code, use the built-in prompt to list all 32 tools, 12 resources, and 7 prompts so you know what the server can do.

/quick-data:list_mcp_assets_prompt

Quick Data Examples

Client configuration

Example claude_desktop_config.json entry for the Quick Data MCP server.

{
  "mcpServers": {
    "quick-data": {
      "command": "uv",
      "args": ["run", "--directory", "/absolute/path/to/quick-data-mcp", "python", "main.py"]
    }
  }
}

Prompts to try

Natural language requests that exercise the server's analytics and visualization tools.

- "Load the file data/sales.csv as the 'sales' dataset and give me a first look at its structure."
- "Find correlations between all numeric columns in the sales dataset."
- "Detect outliers in the order_value column and explain what's unusual about them."
- "Create a bar chart of total revenue by region from the sales dataset."
- "Compare the Q1 and Q2 datasets and highlight the biggest differences in performance metrics."

Troubleshooting Quick Data

Server fails to start with 'command not found: uv'

Install uv with 'curl -LsSf https://astral.sh/uv/install.sh | sh' and ensure it is on your PATH. Use 'which uv' to confirm the binary location, then update the command field in your MCP config with the full path if needed.

Dataset load fails or returns no rows

Confirm the file path passed to load_dataset is an absolute path or is relative to the --directory you configured. CSV files must have a header row. JSON files should be an array of objects at the top level.

MCP client shows no tools after connecting

Verify .mcp.json has the correct absolute path to the project directory. Restart the MCP client after editing the config. Run 'uv run python main.py' in the terminal to check for import errors before retrying.

Frequently Asked Questions about Quick Data

What is Quick Data?

Quick Data is a Model Context Protocol (MCP) server that prompt focused mcp server for .json and .csv agentic data analytics for claude code It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Quick Data?

Follow the installation instructions on the Quick Data GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Quick Data?

Quick Data works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Quick Data free to use?

Yes, Quick Data is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Quick Data Alternatives — Similar Data Science & ML Servers

Looking for alternatives to Quick Data? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.

Ultrarag

★ 5.6k

A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

RocketRide

★ 3.1k

📇 🏠 - MCP server that exposes RocketRide AI pipelines as t

Aix Db

★ 2.1k

Aix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。

NeMo Data Designer

★ 1.9k

🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.

PaperBanana

★ 1.7k

Open source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.

MiniMax

★ 1.5k

Bridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.

Browse More Data Science & ML MCP Servers

Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Data Science & MLBrowse All Servers

Quick Config Preview

{ "mcpServers": { "quick-data": { "command": "npx", "args": ["-y", "quick-data"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Quick Data?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides