W&B Analytics
Complements the official W&B MCP server with advanced analytical capabilities including hyperparameter importance ranking with R² metrics, sweep summaries combining best and worst run analysis, structured run comparisons, and regression detection using z-tests against baseline runs. Generates Plotly charts exported as inline base64 PNG images. Supports relative-date filtering, optional run and sweep actions via --enable-actions flag, local stdio and HTTP bearer-token transports, and OpenTelemetry observability. Requires Python 3.11+.
I/O
heuristic · beta该 skill 无 npm 包,暂用描述启发式推断 I/O;接入后可实测。
综合分
效果测评卡
进行中 · 待运行真实 I/O 已解决「输入输出是什么」;下一步接 agent 真跑,量化「效果好不好」。
@antv/mcp-server-chart is a TypeScript-based server that enables AI assistants to generate data visualizations using AntV's charting capabilities. Developed by the AntV Visualization Team, it implements the Model Context Protocol to provide a standardized interface for creating various chart types from data. The server exposes chart generation functionality that can be accessed through MCP tools, making it particularly valuable for applications that need to produce visual data representations through conversational interfaces without requiring direct knowledge of visualization libraries.
Provides AI assistants with on-demand access to 141 documentation pages, 283 code examples, and 1,098 class API references for amCharts 5. Instead of loading the entire reference into context, the server lets AI query exactly what it needs — specific chart type references, code examples, or API lookups. Supports searching docs, browsing examples by category, and retrieving quick-start templates for any chart type.
CAFE provides AI agents with access to Dangamsoft's classical East Asian knowledge engine for Korean Saju (Four Pillars of Destiny) analysis. Five tools cover full Saju chart generation from birth date and time, five-element (Ohaeng) balance scoring, Gyeokguk pattern classification, Yin-Yang Johu harmony assessment, and Yongshin candidate determination. The underlying engine combines classical theory with machine learning, achieving 91.1% accuracy on five-class Yongshin classification.