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.
@xoniks
Basic information
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
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"
}
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
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.
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.
Python 3.8+, Ollama installed and running, and Claude Desktop installed. A lightweight Ollama model such as `qwen2:0.5b` is recommended.
Data is stored in local DuckDB database files (`.duckdb`). All processing happens on your machine; no data is sent to external services.
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.
Bar, line, scatter, pie, histogram, box, heatmap, and area charts. Chart type suggestions and guided configuration are available through natural language.
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.

Fund Momentum MCP Server — VC intelligence for AI assistants. 1000+ active VC funds, live investor signals, AI-powered startup matching.
The Xata MCP server lets AI assistants and agents interact with your Xata organizations, projects, and Postgres database branches.

Verified golf club data for AI agents: holes, par, address, phone, booking links, facilities, visitor rules and green fees for golf clubs in Spain (Canary Islands and mainland), expanding across Europe. Every fact comes
A Model Context Protocol (MCP) server implementation that provides database capabilities for Chroma
Drop-in Apache Spark replacement written in Rust, unifying batch processing, stream processing, and compute-intensive AI workloads.
Comments