MCP Data Analytics Server

Un potente servidor de análisis de datos construido con FastMCP que proporciona herramientas especializadas para el procesamiento, análisis y visualización de datos, accesible a través de una interfaz web moderna construida con Streamlit.

python

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "edwin1719-mcp-data-analytics-server": {
      "command": "python",
      "args": [
        "server.py"
      ],
      "env": {
        "OPENAI_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

You run the MCP Data Analytics Server to process, analyze, and visualize data through a web interface. It combines a data-processing backend with a Streamlit frontend so you can upload files, perform statistical analyses, create dynamic tables, and visualize results interactively with Plotly.

How to use

Start the MCP server on one terminal to serve data analytics capabilities. In a second terminal, run the Streamlit client to interact with the results through a web UI. Use the available tools to analyze files, generate visualizations, perform data conversions, and fetch external data as needed.

Typical workflows you can perform include:

Analyze a data file to obtain statistics, read properties, and detect types.
Create and read documents for reporting.
Generate interactive charts and tables to explore your dataset.
Convert data between formats such as CSV, JSON, Excel, and Parquet.
Retrieve information from GitHub, scrape web pages, and download files when needed.

How to install

Follow these steps to set up the MCP Data Analytics Server locally and start using the client UI.

How to install

# Prerequisites
Python 3.8+

# 1. Clone the project
git clone https://github.com/Edwin1719/mcp-data-analytics-server.git
cd mcp-data-analytics-server

# 2. Install dependencies
pip install -r requirements.txt

# 3. Configure API key
cp .env.example .env
# Edit .env and add your OPENAI_API_KEY

# 4. Run the server and the client
# Terminal 1: MCP server
python server.py

# Terminal 2: Streamlit client
streamlit run app.py

# Open in browser
# http://localhost:8501

Additional notes

Prerequisites include Python 3.8 or newer and a valid OpenAI API key. The server uses the key to power data processing and natural language interactions. The client UI runs on Streamlit and is accessible via http://localhost:8501 once started.

Security and configuration

Store sensitive keys in a secure environment file. Do not commit your OPENAI_API_KEY to version control. The environment variable OPENAI_API_KEY is required to run the server. You can replace YOUR_API_KEY in the configuration with your actual key.

Available tools

analizar_archivo

Performs a full analysis of file properties, including size, type, and metadata; provides statistics and detects data types.

crear_archivo

Creates new files with specified content and saves them in the designated location.

leer_documento

Reads documents such as PDFs, TXT, and CSV with configurable limits and previews.

analizar_datos

Runs statistical analyses on datasets, generating summary statistics and distributions.

tabla_dinamica_avanzada

Generates advanced pivot tables with aggregations and grouped views.

crear_visualizacion

Creates interactive charts using Plotly (bar, line, etc.) for data exploration.

buscar_repositorios_github

Performs advanced searches on GitHub to discover relevant data science repositories.

extraer_contenido_web

Web scraping with CSS selectors to extract targeted content from web pages.

descargar_archivo_web

Downloads files from given URLs for offline use.

convertir_formato_datos

Converts data between formats such as CSV, JSON, Excel, and Parquet.

Built by

VeilStrat

AI signals for GTM teams