Generates ECharts chart images from LLM-provided data and parameters, returning cloud-hosted image URLs.
別名 apache/echarts-mcp
- スター
- 87
- ツール
- —
- ダウンロード数（30日間）
- —
- 最新バージョン
- —
- 最終コミット
- 2026年11月13日
- ライセンス
- Apache-2.0
Apache ECharts MCPとは
Apache EChartsはMCPサーバーです。 Generates ECharts chart images from LLM-provided data and parameters, returning cloud-hosted image URLs.
プロジェクトのREADMEから生成された概要
Apache ECharts MCP server について
Visualizing data through Apache ECharts charts from within an AI chat interface is the primary function of this server. It accepts specific parameters like series type, data, seriesName, title, and axisName from an LLM to generate visual representations. The server supports various series types including bar, line, pie, scatter, funnel, tree, treemap, and sunburst.
Developers use this tool by installing it via npm and configuring an environment file. It requires a baidubce/bce-sdk-js account to handle cloud storage for the resulting images. Once the chart is generated, the server returns a cloud-hosted image URL directly to the client. While the implementation defaults to specific themes, developers can modify the storage logic in src/storage.js or adjust themes and fonts within the source code.
できること
- 1Generate specific chart typesAsk the AI to create a bar or pie chart using a provided dataset.
- 2Create stable data visualizationsRequest a chart using minimal parameters to ensure consistent and reliable output.
- 3Store charts in cloud storageAutomatically upload generated chart images to a cloud provider and receive a URL.
プロジェクトの README から作成されています。すべてのユースケースは、その引用と照らし合わせて確認されています。
自動チェック
実行日 2026年11月15日完全なレポート →まだ検証されていません。サーバーには80点のスコア、重大な問題がないこと、および検証に必要な十分なデータが必要です。 チェックの仕組み · 点数を上げるための改善点
- ソースリポジトリがリンクされており、アクセス可能apache/echarts-mcp is public and reachablegithub.com/apache/echarts-mcp ↗合格
- パッケージがこのリポジトリをソースとして指定未チェック
- ビルドの来歴 (Sigstore 証明)未チェック
- オープンソースライセンス (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗合格
- 過去1年以内にコミットまたはリリースありLast commit or release 2026-11-13github.com/apache/echarts-mcp ↗合格
- OpenSSF Scorecard未チェック
- パッケージ名が有名なパッケージに酷似していない未チェック
- パッケージおよびその依存関係に重大な勧告なし未チェック
- モデルへの隠れた指示がない0 tool descriptions and the README read; no override phrases, credential paths or hidden characters合格
- 破壊的なツールがラベル付けされている未チェック
- リモートエンドポイントが MCP ハンドシェイクに応答未チェック
README
GitHubで見るECharts MCP
This project shows how to implement an MCP (Model Context Protocol) server of Apache ECharts.
The basic workflow is that it gets chart type, data and other parameters from an LLM, and returns the cloud image URL of the generated ECharts chart.
Supported ECharts series types: 'bar', 'line', 'pie', 'scatter', 'funnel', 'tree', 'treemap', 'sunburst'.
Setup
npm install
Create an .env file. See .env.example for reference. You need to have the access to a baidubce/bce-sdk-js account to store the images on the cloud.
Run
# Run the MCP server
npm run dev
# Run the inspector in another terminal
npm run inspect
FAQ
How to change image cloud storage?
By default, it uses baidubce/bce-sdk-js to store the generated image and return the URL of the image on the cloud. If you wish to use other Cloud storage, change the implemenation in src/storage.js.
How to change ECharts theme?
See registerTheme and registerFont comments in src/chart.js.
How to support more series types?
- Change
inputSchemainsrc/index.js - Normalize
datainsrc/chart.js
You are welcomed to make a pull request.
Discussion of Implementation
To make an MCP server of Apache ECharts, there are 3 common ways to do:
- Ask LLM to provide a full ECharts option
- Ask LLM to provide pre-fined parameters including chart themes
- Ask LLM to provide pre-fined minimal parameters
The advantage of Approach 1 is that is has the potential of making all kinds of charts that ECharts supports. But it may not be stable, especially for less frequently used chart types.
Approach 2 gives the freedom to change chart themes from prompt. For example, you may ask the LLM to generate a chart with red bars of data .... But this approach requires a lot of parameters in order to support so many ECharts options. And it degenerates to approach 1 as the number of parameters grows.
Approach 3 asks LLM to provide minimal parameters like series type, data, seriesName, title, and axisName. The chart theme is defined in the app so that only the developer of this app, rather than users can change the theme. We believe this is the best way to provide stable results and so this is the approach we take in this project.
Apache ECharts MCPのよくある質問
How can I use a different cloud storage provider for the images?
You can change the storage implementation by modifying the code in src/storage.js.
How do I modify the ECharts theme?
Theme modifications can be made by following the registerTheme and registerFont comments located in src/chart.js.
What chart types are supported by this server?
The server supports bar, line, pie, scatter, funnel, tree, treemap, and sunburst series types.