MCP Data Analyzer

Provides data loading, analysis, and visualization for `.xlsx` and `.csv` files via MCP clients.

other

1

GitHub Stars

other

Language

3 months ago

First Indexed

3 weeks 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": {
    "ouchinikaeru-mcp_data_analyzer": {
      "command": "uv",
      "args": [
        "--directory",
        "/path_to_mcp_data_analyzer/src/mcp_data_analyzer",
        "run",
        "mcp_data_analyzer"
      ]
    }
  }
}

You can run and connect to the MCP Data Analyzer server to load Excel and CSV files, perform statistical analysis, and generate visualizations with familiar tools. This server exposes a straightforward local runtime you can start with a lightweight CLI runner and then interact with from your MCP client to analyze datasets and create graphs.

How to use

To use the MCP Data Analyzer, start the local MCP server and connect with your MCP client. You will load .xlsx or .csv data sources, run statistical analyses, and generate graphs and charts using common visualization libraries. Your client can initiate the data loading, trigger analyses, and request various visual outputs such as charts and plots.

How to install

Prerequisites: you need Git and the MCP runtime tool available on your system.

Clone the project repository, enter the directory, and synchronize dependencies with the MCP runtime tool.

git clone https://github.com/OuchiniKaeru/mcp_data_analyzer.git
cd mcp_data_analyzer
uv sync

Additional configuration and examples

You can run the server in development mode (local runtime) or publish it for remote access. Below are explicit MCP server configurations showing how to start the server in each mode.

{
  "mcpServers": {
    "mcp_data_analyzer": {
      "command": "uv",
      "args": [
        "--directory",
        "/path_to_mcp_data_analyzer/src/mcp_data_analyzer",
        "run",
        "mcp_data_analyzer"
      ]
    }
  }
}

More details on published vs development modes

Development mode uses a local directory path and a run command to start the analyzer. Published mode runs a packaged server that can be accessed remotely.

{
  "mcpServers": {
    "mcp_data_analyzer": {
      "command": "uvx",
      "args": [
        "mcp_data_analyzer"
      ]
    }
  }
}

Available tools

load_and_analyze

Loads .xlsx and .csv files and performs statistical analysis to extract meaningful metrics from data sources.

visualize

Generates graphs and charts using Matplotlib and Plotly to visualize analysis results.