F
licenseNot graded
qualityD
maintenanceA Model Context Protocol (MCP) server implementation that provides the LLM an interface for visualizing data using Vega-Lite syntax.
100
-
root-ext-viz
by graphgrow
Related Servers
Alternatives to root-ext-viz
No user-submitted related servers found.
Related Servers
- AlicenseAqualityBmaintenanceMCP server for creating interactive Vega-Lite data visualizations that render inline in chat via MCP Apps.21MIT
- AlicenseAqualityDmaintenanceA MCP server for data visualization. It exposes tools to render charts (line, bar, pie, scatter, heatmap, etc.) from data and returns plots as either image/text/mermaid diagram.24MIT
- AlicenseAqualityCmaintenanceA comprehensive MCP server that provides intelligent access to the HoloViz ecosystem, enabling AI assistants to help you build interactive dashboards and data visualizations with Panel, hvPlot, Lumen, Datashader, and your favorite Python libraries.2034BSD 3-Clause
- AlicenseNot gradedqualityBmaintenanceMCP server that turns coding agents into data analysts: attach CSV/Parquet/JSON/XLSX or databases, profile data, run read-only SQL, and render Vega-Lite charts as SVG files.1MIT
- AlicenseAqualityDmaintenanceAn MCP server that enables AI assistants to create interactive visualizations, perform statistical analysis, run auto-EDA, and build dashboards using the HoloViz ecosystem with self-contained HTML output.36MIT
TDQS
A4.2/5.0
Scored across 8 tools
Disambiguation5/5
Each tool addresses a distinct stage of the visualization workflow: profiling, loading, state inspection, Python execution, reset, spec creation, export, and recipes. No two tools have overlapping purposes; data_profile describes a file, data_load imports it, and chart_spec creates a chart while chart_export converts existing specs.
Naming Consistency4/5
Tool names predominantly use snake_case with grouped prefixes (data_*, session_*, chart_*), but not all follow a strict verb_noun pattern (e.g., session_state, chart_spec, viz_recipes). Minor deviations in parts of speech do not significantly impede predictability.
Tool Count5/5
Eight tools is within the ideal range for a visualization server. Each tool covers a necessary function—data intake, kernel control, transformation, chart authoring, and output—without redundancy or bloat.
Completeness5/5
The tool surface covers the full lifecycle from data profiling and loading, to transformation via Python, to chart specification, rendering, and export, plus session management and recipe templates. There are no evident gaps for the stated purpose of creating and exporting visualizations.
Maintenance
ActivityMaintained
ResponsivenessNo issues