Mcp Vegalite Server

What is Mcp Vegalite Server about?

Mcp Vegalite Server implements two core tools that let LLMs store tabular data on the server and generate visualizations with Vega‑Lite. It can return the complete specification for downstream processing or a rendered PNG image.

How to use Mcp Vegalite Server?

Add the server to your Claude Desktop configuration (or any MCP‑compatible client) with the following JSON snippet:

{
  "mcpServers": {
    "datavis": {
      "command": "uv",
      "args": [
        "--directory",
        "/absolute/path/to/mcp-datavis-server",
        "run",
        "mcp_server_datavis",
        "--output_type",
        "png"  // or "text"
      ]
    }
  }
}

Then invoke the save_data and visualize_data tools from the LLM, supplying the required arguments.

Key Features

• save_data: Persist a table of aggregations on the server for later use.
• visualize_data: Render a stored table using a user‑provided Vega‑Lite JSON specification.
• Dual output modes: text returns the full spec with embedded data; png returns a base64 PNG via the ImageContent container.
• Simple integration with Claude Desktop and other MCP‑compatible clients.

Use Cases

• LLM‑driven data exploration within a conversational interface.
• Automated report generation where visualizations are created on‑the‑fly.
• Embedding dynamic charts in chat applications without requiring the client to run Vega‑Lite locally.

FAQ

Q: How do I store data for later visualization? A: Call the save_data tool with a unique name and an array of objects representing the table.

Q: Which output types are supported? A: text returns the full Vega‑Lite spec; png returns a base64‑encoded PNG image.

Q: Do I need to know Vega‑Lite syntax? A: Yes, you supply a JSON Vega‑Lite specification when calling visualize_data.

Q: Can I change the output format? A: Set the --output_type argument to either text or png in the server configuration.

Q: Where does the PNG image go? A: It is returned inside the MCP ImageContent container, ready for the client to display.

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"
        ]
    }
  }
}