V
Vega-Lite
community
ai
Generate visualizations from fetched data using the VegaLite format and renderer.
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:
(string): Name of the data table to be savedname
(array): Array of objects representing the data tabledata
- Returns: success message
visualize_data
- Visualize a table of data using Vega-Lite syntax
- Input:
(string): Name of the data table to be visualizeddata_name
(string): JSON string representing the Vega-Lite specificationvegalite_specification
- Returns: If the
is set to--output_type
, returns a success message with an additionaltext
key containing the complete Vega-Lite specification with data. If theartifact
is set to--output_type
, returns a base64 encoded PNG image of the visualization using the MPCpng
container.ImageContent
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" ] } } }
Related Servers

AgentQL
official
Enable AI agents to get structured data from unstructured web with [AgentQL](https://www.agentql.com/).
View Details
BICScan
official
Risk score / asset holdings of EVM blockchain address (EOA, CA, ENS) and even domain names.
View DetailsChronulus AI
official
Predict anything with Chronulus AI forecasting and prediction agents.
View Details