Mermaid MCP server

The Mermaid MCP Server implements the Model Context Protocol (MCP) to enable Large Language Model applications to seamlessly integrate with mermaid.js visualizations. This server acts as a bridge between LLMs and mermaid.js, allowing for dynamic diagram generation directly from your AI applications.

Installation Options

Quick Installation via Smithery

The easiest way to install the Mermaid MCP Server for Claude Desktop is through Smithery:

npx -y @smithery/cli install @longjianjiang/mermaid-mcp-server --client claude

Manual Installation

If you prefer to install manually:

1. Clone the repository
2. Install dependencies
3. Start the server

# Clone the repository
git clone [repository-url]

# Install dependencies
npm install

# Start the server
npm start

Usage Guide

Connecting to the Server

Connect your LLM application to the running MCP server to begin generating diagrams. The server follows the MCP 1.0 specification, allowing standardized communication with LLM clients.

Generating Diagrams

You can generate mermaid.js diagrams by using MCP methods:

• tools/call - To invoke diagram generation
• resources/read - To access diagram resources

Example Workflow

1. Connect your LLM application to the server
2. Pass mermaid syntax to the server
3. Receive and display the generated diagram

Configuration

To customize the server behavior, modify the config.json file. Configuration options include:

• Server port settings
• Path restrictions
• Output formats
• Security settings

Example configuration adjustment:

{
  "port": 3000,
  "allowedPaths": ["diagrams", "templates"],
  "outputFormat": "svg"
}

Features

Core Capabilities

• Secure Interface: Generate mermaid diagrams through a protected API
• MCP Compliance: Full compatibility with Model Context Protocol 1.0
• Performance Optimized: Designed for scalability and responsiveness
• Extensible Architecture: Easy to enhance with additional visualization tools

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.