Chhart MCP

Name: Chhart MCP
Author: alwank

@alwank

リポジトリ

Chhart MCP について

Enable your AI assistant to generate instant, shareable flowcharts and Sankey diagrams directly in chat.

#productivity #flowchart

基本情報

カテゴリ

AI とエージェント

トランスポート

stdio

公開者

alwank

投稿者

Alwan Alkautsar

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": {
    "chhart": {
      "url": "https://mcp.chhart.app/mcp"
    }
  }
}

ツール

Create a flowchart on chhart.app using text-based DSL syntax. Returns a shareable URL to view and edit the flowchart.

Create a Sankey diagram on chhart.app showing flows between nodes. Returns a shareable URL to view and edit the diagram.

Get documentation and examples for Chhart's flowchart and Sankey diagram syntax.

概要

What is Chhart MCP?

Chhart MCP bridges the gap between text-based AI and visual thinking. It enables LLMs like Claude and ChatGPT to programmatically generate flowcharts and Sankey diagrams using a simple text-based DSL.

How to use Chhart MCP?

Install Chhart MCP as an MCP server in your AI client. The AI can then invoke the tools to generate diagrams, which produce shareable URLs hosted on chhart.app. No configuration keys are required beyond standard MCP setup.

Key features of Chhart MCP

AI-native flowcharts: decision trees, process maps, architecture diagrams
Sankey diagrams: data flows, budget splits, traffic analysis
Stateless sharing: zero-database architecture, all data in the URL hash
Syntax awareness: tools for the AI to learn and validate the DSL

Use cases of Chhart MCP

Generate decision trees and process maps from natural language descriptions
Visualize architecture diagrams and system flows with an AI assistant
Create Sankey diagrams for budget allocation or traffic analysis
Share editable diagrams via privacy-friendly, self-contained URLs

FAQ from Chhart MCP

What makes Chhart MCP different from other diagramming tools?

Chhart MCP is completely stateless—diagram data is encoded directly into the shareable URL hash. No database storage is required, and diagrams are instantly editable on chhart.app.

What are the runtime requirements?

Any MCP-compatible client (e.g., Claude Desktop, ChatGPT) can use Chhart MCP. No additional rendering engine or dependencies are needed beyond the server itself.

Where does my diagram data live?

All diagram data is stored in the URL hash of the generated link. No data is stored on any server; the URL is the only copy. You can manage sharing and privacy yourself.

Are there any known limits?

The README does not list specific limits. Since data is URL-encoded, very large diagrams may exceed practical URL length constraints in some clients.

What transport or authentication is used?

Chhart MCP uses standard MCP transport (stdio or HTTP, depending on configuration). No authentication is mentioned; the server is designed for local or trusted environments.