MCP.so
Sign In

Mcp Data Visualization Server

@xoniks

About Mcp Data Visualization Server

Transform natural language into beautiful, interactive data visualizations. This server uniquely integrates powerful technologies like DuckDB, Ollama, and Plotly, streamlining complex data analysis workflows into a single, conversational experience within the Model Context Protoc

Basic information

Category

Databases

Transports

stdio

Publisher

xoniks

Submitted by

Egezon Baruti

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "data-viz-server": {
      "command": "C:/Github/mcp-visualization-duckdb/.venv/Scripts/python.exe",
      "args": [
        "C:/Github/mcp-visualization-duckdb/mcp_server.py"
      ],
      "cwd": "C:/Github/mcp-visualization-duckdb",
      "env": {
        "DUCKDB_DATABASE_PATH": "C:/Github/mcp-visualization-duckdb/data/mcp.duckdb",
        "PYTHONIOENCODING": "utf-8"
      }
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Mcp Data Visualization Server?

A Model Context Protocol server that transforms natural language into interactive data visualizations using DuckDB for data storage, Plotly for chart generation, and Ollama for local LLM processing. It integrates with Claude Desktop to let users manage databases, analyze data, and create charts through conversational commands.

How to use Mcp Data Visualization Server?

Install Python 3.8+, Ollama, and Claude Desktop. Clone the repository, create a virtual environment, install dependencies (mcp, duckdb, pandas, plotly, ollama, etc.), start Ollama, pull a model (e.g., qwen2:0.5b), and add the server configuration to Claude Desktop’s claude_desktop_config.json. Restart Claude Desktop and chat using natural language requests.

Key features of Mcp Data Visualization Server

  • Natural language interface for database management and chart creation
  • Interactive charts (bar, line, scatter, pie, histogram, box, heatmap, area)
  • Flexible database switching with an interactive browser
  • Local LLM processing via Ollama for privacy
  • Automatic statistical insights and pattern detection
  • SQL injection protection and input validation

Use cases of Mcp Data Visualization Server

  • Business analytics: sales dashboards, customer segmentation, regional performance
  • Data science: exploratory analysis, correlation heatmaps, outlier detection
  • Quick ad‑hoc queries and visualizations without writing SQL or code
  • Privacy‑focused analysis where all data stays on the local machine

FAQ from Mcp Data Visualization Server

What are the prerequisites for running the server?

Python 3.8+, Ollama installed and running, and Claude Desktop installed. A lightweight Ollama model such as qwen2:0.5b is recommended.

How is data stored and processed?

Data is stored in local DuckDB database files (.duckdb). All processing happens on your machine; no data is sent to external services.

Does the server require an internet connection?

No. The LLM runs locally via Ollama, and all database operations are local. An internet connection is only needed for initial installation of dependencies or pulling an Ollama model.

What chart types are available?

Bar, line, scatter, pie, histogram, box, heatmap, and area charts. Chart type suggestions and guided configuration are available through natural language.

How can I switch to a different database?

Use natural language commands like “Switch to in-memory database” or “Connect to C:/path/to/database.duckdb”, or use the browse_databases and change_database tools.

Comments

More Databases MCP servers