What is Vega-Lite Data Visualization

The Data Visualization MCP Server is an implementation of the Model Context Protocol (MCP) that provides a structured interface for Large Language Models (LLMs) to create visual representations of data using Vega-Lite syntax.

Use cases

This server can be utilized for visualizing data aggregates in various domains such as business intelligence, academic research, and data journalism, making it easier to interpret complex data through graphical representations.

How to use

Users can set up the server by configuring it in the claude_desktop_config.json file, specifying the server command and the desired output type (either ‘png’ for image output or ‘text’ for textual output). The server provides functions to save data and visualize it using specified Vega-Lite schemas.

Key features

Key features of the server include the ability to save data tables for later visualization and to generate visualizations based on Vega-Lite specifications. It supports various output formats for the generated visuals, enhancing flexibility for users.

Where to use

The MCP server can be implemented in environments where data visualization is required, such as within data science pipelines, web applications, or integrated with LLMs for automated reporting and analysis tasks.

Data Visualization MCP Server

Overview

A Model Context Protocol (MCP) server implementation that provides the LLM an interface for visualizing data using Vega-Lite syntax.

Components

Tools

The server offers two core tools:

• save_data
  • Save a table of data agregations to the server for later visualization
  • Input:
    • name (string): Name of the data table to be saved
    • data (array): Array of objects representing the data table
  • Returns: success message
• visualize_data
  • Visualize a table of data using Vega-Lite syntax
  • Input:
    • data_name (string): Name of the data table to be visualized
    • vegalite_specification (string): JSON string representing the Vega-Lite specification
  • Returns: If the --output_type is set to text, returns a success message with an additional artifact key containing the complete Vega-Lite specification with data. If the --output_type is set to png, returns a base64 encoded PNG image of the visualization using the MPC ImageContent container.

Usage with Claude Desktop

# Add the server to your claude_desktop_config.json
{
  "mcpServers": {
    "datavis": {
        "command": "uv",
        "args": [
            "--directory",
            "/absolute/path/to/mcp-datavis-server",
            "run",
            "mcp_server_datavis",
            "--output_type",
            "png" # or "text"
        ]
    }
  }
}