drio
Open app

Data Visualization MCP Server

Source

Catalog onlyCatalog onlySTDIO

Overview

Data Visualization MCP Server is a server implementation that integrates with LLMs to provide effective data visualization through the Vega-Lite syntax, leveraging the Model Context Protocol (MCP).

To use the server, you must configure it with your local setup and utilize its core functions: save data for later visualization and visualize existing data using Vega-Lite specifications. Code samples are provided for seamless integration with Claude Desktop.

  • Save data tables for easy retrieval and visualization - Generate visualizations in various formats (text or PNG) - Integration with LLMs for enhanced data analysis capabilities
  1. Saving and visualizing experimental data for research projects.
  2. Creating live dashboards for real-time data analysis.
  3. Enabling data scientists to visualize complex datasets easily.

Add to your AI client

Use these steps to connect Data Visualization MCP Server in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "mcp-vegalite-server-isaacwasserman": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-vegalite-server-isaacwasserman"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "mcp-vegalite-server-isaacwasserman": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-vegalite-server-isaacwasserman"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "mcp-vegalite-server-isaacwasserman": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-vegalite-server-isaacwasserman"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "mcp-vegalite-server-isaacwasserman": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-vegalite-server-isaacwasserman"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp-vegalite-server-isaacwasserman": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-vegalite-server-isaacwasserman"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "mcp-vegalite-server-isaacwasserman": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-vegalite-server-isaacwasserman"
      ]
    }
  }
}

FAQ

What types of data can I save?

You can save any table of data aggregations as long as it is represented as an array of objects.

What formats can the visualizations be output in?

Visualizations can be output as plain text containing Vega-Lite specifications, or as base64 encoded PNG images.

Is there any specific setup required for using this server?

Yes, you need to add the server configuration to your claude_desktop_config.json for it to function properly.7:["$","div",null,{"className":"container mx-auto flex flex-col gap-4","children":["$L26","$L27",["$","$L28",null,{"currentProject":{"id":210,"uuid":"225ba2ba-32ce-4253-a081-96c8fe041cf3","name":"mcp-vegalite-server","title":"Data Visualization MCP Server","description":"","avatar_url":"https://avatars.githubusercontent.com/u/1498116?v=4","created_at":"2024-12-13T09:12:51.643Z","updated_at":"2024-12-13T12:28:12.927Z","status":"created","author_name":"isaacwasserman","author_avatar_url":"https://avatars.githubusercontent.com/u/1498116?v=4","tags":"[]","category":"research-and-data","is_featured":false,"sort":1,"url":"https://github.com/isaacwasserman/mcp-vegalite-server","target":"_self","content":"$29","summary":"$2a","img_url":"https://camo.githubusercontent.com/0b117dbf31c0fe842420860dba506b2d104a0a3e3d3b4d084b6273dcbaa06b2b/68747470733a2f2f6d736565702e6e65742f70722f69736161637761737365726d616e2d6d63702d766567616c6974652d7365727665722d62616467652e706e67","type":null,"metadata":"{\"star\":\"71\",\"license\":\"\",\"language\":\"Python\",\"is_official\":false,\"latest_commit_time\":\"2025-05-16 12:44:35\"}","user_uuid":null,"tools":null,"sse_url":null,"sse_provider":null,"sse_params":null,"is_official":false,"server_command":null,"server_params":null,"server_config":null,"allow_call":false,"is_innovation":false,"is_dxt":false,"dxt_manifest":null,"dxt_file_url":null,"is_audit":false},"randomProjects":[],"currentServerKey":"$undefined"}]]}]

Research and data
Data Visualization MCP Server — MCP Registry