広告掲載
MCP.so
ログイン

Data Visualization MCP Server

@Mavline

リポジトリ

基本情報

カテゴリ

データと分析

トランスポート

stdio

作者

Mavline

Data Visualization MCP Server について

LLM-connected data visualization workflow using Vega-Lite.

#data-visualization#mcp-server#vega-lite

Data Visualization MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "mcp-server-vegalite": {
      "command": "uv",
      "args": [
        "sync"
      ]
    }
  }
}

Data Visualization MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Data Visualization MCP Server?

Data Visualization MCP Server is a Model Context Protocol server that enables LLM-connected workflows to store tabular data and render Vega-Lite visualizations. It provides a technical integration layer for AI-assisted reporting, data visualization, and analytics prototypes where an LLM needs to turn structured data into charts without manual tool switching.

How to use Data Visualization MCP Server?

Install using uv or another Python environment manager with Python 3.10+. Run the server with uv run mcp_server_vegalite --output-type png for PNG output or uv run mcp_server_vegalite --output-type text for text/spec artifacts. The server exposes two core tools: one to save a named table of JSON-like rows, and another to accept a Vega-Lite specification, attach the saved data, render the chart, and return the result.

Key features of Data Visualization MCP Server

  • Save named tabular datasets for later visualization.
  • Generate Vega-Lite visualizations from saved datasets.
  • Return visualization output as text/spec or PNG images.
  • Support stdio transport for local MCP clients.
  • Include an SSE/FastAPI path for integration experiments.
  • Store generated visualization files locally during runs.

Use cases of Data Visualization MCP Server

  • AI-assisted reporting: an LLM produces a chart from structured query results.
  • Data visualization workflows: turn tabular data into charts without manual tool switching.
  • Analytics prototypes: quickly generate Vega-Lite specs from language-model outputs.
  • Integration layers between LLMs and business data for dashboards or reports.
  • Portfolio/proof-of-work projects demonstrating LLM-connected data visualization.

よくある質問

1

What are the runtime requirements?

Python 3.10 or newer and `uv` (or another Python environment manager) are required.

2

What transport protocols does the server support?

The server supports stdio transport for local MCP clients and includes an SSE/FastAPI path for integration experiments.

3

Can the server return images?

Yes. Run with `--output-type png` to return PNG images, or `--output-type text` to return Vega-Lite specification text.

4

What kind of data can be saved and visualized?

The server saves named tables of JSON-like rows. Vega-Lite specifications are attached to this saved data for rendering.

5

Where are generated visualization files stored?

Generated visualization files are stored locally during runs. No private client data, production credentials, or internal datasets are included.

コメント

「データと分析」の他のコンテンツ

Signal Nodus SEC Filings

Signal Nodus

Primary-source SEC intelligence for AI agents, delivered over MCP. 27 tools: year-over-year filing diffs, 8-K material events, 13D/13G activist stakes, insider Form 4 trades, 13F institutional holdings, IPO pipeline, ful

Forency

cheevahagadog

Investigate any website's technology stack: CMS, eCommerce, frameworks, analytics, CRM, payments, and hosting behind any URL. Ask "which of these 15 prospects use HubSpot vs Salesforce?" and get a table back. Free tier:

1

App Store Tracker

Top In It

iOS App Store data for AI agents: chart rankings, app details, reviews, keywords, ads and revenue estimates for any app in any country.

Instagram MCP Server

HasData

Read public Instagram profiles and post feeds by handle in Claude, Cursor, and other MCP clients. Get follower counts, captions, hashtags, mentions, and engagement counts as structured JSON.

23

Subtext

Subtext by Fullstory

Session replay, built for agents. Subtext is agentic session review: it captures production sessions of your app and connects them to your coding agent — Claude Code, Cursor, Codex, Devin, your own harness — so it can

9
広告掲載