
Chhart MCP
@alwank
About Chhart MCP
Enable your AI assistant to generate instant, shareable flowcharts and Sankey diagrams directly in chat.
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"chhart": {
"url": "https://mcp.chhart.app/mcp"
}
}
}Tools
3Create 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.
Overview
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.
More AI & Agents MCP servers
1MCP - One MCP Server for All
1mcp-appA unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.
Mcp Agent
lastmile-aiBuild effective agents using Model Context Protocol and simple workflow patterns
1Panel
1Panel-dev🔥 1Panel is a modern, open-source VPS control panel — and the only one with native AI agent support. Run Ollama models, deploy OpenClaw agents, and manage your entire server stack from one clean web interface.
MCP Manager for Claude Desktop
zueaisimple web ui to manage mcp (model context protocol) servers in the claude app
mcp-hfspace MCP Server 🤗
evalstateMCP Server to Use HuggingFace spaces, easy configuration and Claude Desktop mode.
Comments