RapidChart

Generates and updates RapidChart diagrams from code via Cursor MCP client with token-based authentication and multiple AI models.

python

GitHub Stars

python

Language

6 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "samicostox-rapidchart-mcp": {
      "command": "python",
      "args": [
        "-m",
        "rapidchart_mcp"
      ],
      "env": {
        "RAPIDCHART_API_URL": "https://fastuml-0bb6938ba599.herokuapp.com",
        "RAPIDCHART_API_TOKEN": "rc_your_token_here",
        "RAPIDCHART_GUIDELINES": "true",
        "RAPIDCHART_FEW_PROMPTS": "false",
        "RAPIDCHART_DEFAULT_TYPE": "general"
      }
    }
  }
}

You can run a RapidChart MCP Server to generate and manage diagrams directly from Cursor, enabling you to create class, ER, sequence, and architecture diagrams from code, update them as your code changes, and organize them in workspaces and folders with tokens and model options for secure, scalable diagramming.

How to use

You interact with the RapidChart MCP Server through your MCP client in Cursor. After you configure the server, you can ask it to generate diagrams from your source code, list available AI models and your credits, and update existing diagrams with new code. Use natural language prompts to generate diagrams, such as asking for a class diagram from a Python file or updating a diagram with fresh code. You can also browse your diagrams, move them between folders or workspaces, and manage them from the same interface.

How to install

Prerequisites: Python must be installed on your system.

Install the MCP server package using Python’s package manager.

Step 1: Install the package using pip.

pip install rapidchart-mcp

Configuration and usage notes

Configure Cursor to connect to the MCP server using the local stdio-based run command and environment variables shown here.

{
  "mcpServers": {
    "rapidchart": {
      "command": "python",
      "args": ["-m", "rapidchart_mcp"],
      "env": {
        "RAPIDCHART_API_TOKEN": "rc_your_token_here",
        "RAPIDCHART_API_URL": "https://fastuml-0bb6938ba599.herokuapp.com",
        "RAPIDCHART_DEFAULT_TYPE": "general",
        "RAPIDCHART_FEW_PROMPTS": "false",
        "RAPIDCHART_GUIDELINES": "true"
      }
    }
  }
}

Environment and security

Your RapidChart API token and API URL are required to authenticate requests and access your diagram credits. Keep your token secret and only share it with trusted tools and environments.

Troubleshooting

If you encounter a 503 timeout while creating diagrams, it may be a temporary routing limitation. The diagram is still created; check your diagrams list to confirm. If generation is slow, try smaller diagrams or simpler code.

Examples

Create a new class diagram from a file and then update it with new code later.

Notes

The MCP server supports multiple AI models and respects your RapidChart credits and API keys. You can tailor the default diagram type and prompts through environment variables.

Available tools

list_models

Show available AI models and your credits/status for each model.

list_workspaces

List your workspaces.

list_folders

List folders in a workspace.

list_diagrams

Browse your diagrams.

create_diagram

Generate a diagram from provided code or context.

get_diagram

Get details for a specific diagram.

update_diagram

Update a diagram with new code or context.

delete_diagram

Delete a diagram.

move_diagram

Move a diagram to a different folder or workspace.

Built by

VeilStrat

AI signals for GTM teams