MCP Mermaid

AI-powered dynamic generation of Mermaid diagrams via the Model Context Protocol.

View on GitHub Visit Website

283

Stars

Forks

283

Watchers

Issues

MCP Mermaid enables dynamic generation of Mermaid diagrams and charts using AI via the Model Context Protocol (MCP). It supports all features and syntax of Mermaid, and can export diagrams in various formats including SVG, base64, and files. The server can be run locally or globally using different transport protocols such as stdio, SSE, or streamable, making it compatible with tools like Claude, VSCode, and Smithery. It provides customization for background color and theme, and validates output to ensure correct syntax and graphics.

Key Features

Full support for Mermaid syntax and features

Configurable background color and themes

Multiple export formats: base64, SVG, Mermaid source, and file

Validation of diagram syntax and graphics

Runs as an MCP server with stdio, SSE, or streamable transport protocols

CLI interface with various configurable options

Seamless integration with desktop AI tools like VSCode and Claude

Support for multi-round AI model output

Local and global installation options

Compatibility with platforms like aliyun, modelscope, smithery.ai

Use Cases

Automatically generating flowcharts and sequence diagrams from AI prompts

Embedding dynamically created diagrams into documentation systems

Integrating visual diagram creation with AI chat tools in developer workflows

Enabling AI agents to output visual explanations and workflows

Validating and correcting Mermaid syntax through multi-round interaction

Exporting diagrams for presentations or technical documentation

Enhancing data storytelling with auto-generated charts and graphs

Building collaborative diagramming tools using server-side rendering

Providing visualization capabilities to custom AI-powered applications

Automating interactive dashboard or map creation via AI assistants

README

MCP Mermaid

Generate mermaid diagram and chart with AI MCP dynamically. Also you can use mcp-server-chart to generate chart, graph, map.

✨ Features

Fully support all features and syntax of Mermaid.
Support configuration of backgroundColor and theme, enabling large AI models to output rich style configurations.
Support exporting to base64, svg, mermaid, and file formats, with validation for Mermaid to facilitate the model's multi-round output of correct syntax and graphics. Use outputType: "file" to automatically save PNG diagrams to disk for AI agents.

🤖 Usage

To use with Desktop APP, such as Claude, VSCode, Cline, Cherry Studio, and so on, add the MCP server config below. On Mac system:

json

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

On Window system:

json

{
  "mcpServers": {
    "mcp-mermaid": {
      "command": "cmd",
      "args": [
        "/c",
        "npx",
        "-y",
        "mcp-mermaid"
      ]
    }
  }
}

Also, you can use it on aliyun, modelscope, glama.ai, smithery.ai or others with HTTP, SSE Protocol.

🚰 Run with SSE or Streamable transport

Option 1: Global Installation

Install the package globally:

bash

npm install -g mcp-mermaid

Run the server with your preferred transport option:

bash

# For SSE transport (default endpoint: /sse)
mcp-mermaid -t sse

# For Streamable transport with custom endpoint
mcp-mermaid -t streamable

Option 2: Local Development

If you're working with the source code locally:

bash

# Clone and setup
git clone https://github.com/hustcc/mcp-mermaid.git
cd mcp-mermaid
npm install
npm run build

# Run with npm scripts
npm run start:sse        # SSE transport on port 3033
npm run start:streamable # Streamable transport on port 1122

Access Points

Then you can access the server at:

SSE transport: http://localhost:3033/sse
Streamable transport: http://localhost:1122/mcp (local) or http://localhost:3033/mcp (global)

🎮 CLI Options

You can also use the following CLI options when running the MCP server. Command options by run cli with -h.

plain

MCP Mermaid CLI

Options:
  --transport, -t  Specify the transport protocol: "stdio", "sse", or "streamable" (default: "stdio")
  --port, -p       Specify the port for SSE or streamable transport (default: 3033)
  --endpoint, -e   Specify the endpoint for the transport:
                    - For SSE: default is "/sse"
                    - For streamable: default is "/mcp"
  --help, -h       Show this help message

🔨 Development

Install dependencies:

bash

npm install

Build the server:

bash

npm run build

Start the MCP server

Using MCP Inspector (for debugging):

bash

npm run start

Using different transport protocols:

bash

# SSE transport (Server-Sent Events)
npm run start:sse

# Streamable HTTP transport
npm run start:streamable

Direct node commands:

bash

# SSE transport on port 3033
node build/index.js --transport sse --port 3033

# Streamable HTTP transport on port 1122
node build/index.js --transport streamable --port 1122

# STDIO transport (for MCP client integration)
node build/index.js --transport stdio

📄 License

MIT@hustcc.

Star History

Repository Owner

hustcc

User

Repository Details

Language TypeScript

Default Branch main

Size 43 KB

Contributors 7

License MIT License

MCP Verified Nov 11, 2025

Programming Languages

TypeScript

83.79%

JavaScript

13.87%

Dockerfile

2.02%

Shell

0.32%

Topics

mcp mcp-server mermaid mermaidjs

Join Our Newsletter

Stay updated with the latest AI tools, news, and offers by subscribing to our weekly newsletter.

Related MCPs

Discover similar Model Context Protocol servers

Mindpilot MCP

Visualize and understand code structures with on-demand diagrams for AI coding assistants.

Mindpilot MCP provides AI coding agents with the capability to visualize, analyze, and understand complex codebases through interactive diagrams. It operates as a Model Context Protocol (MCP) server, enabling seamless integration with multiple development environments such as VS Code, Cursor, Windsurf, Zed, and Claude Code. Mindpilot ensures local processing for privacy, supports multi-client connections, and offers robust configuration options for server operation and data management. Users can export diagrams and adjust analytics settings for improved user control.

⭐ 61
MCP
abrinsmead/mindpilot-mcp

Markmap MCP Server

Convert Markdown to interactive mind maps via the Model Context Protocol.

Markmap MCP Server enables seamless conversion of Markdown content into interactive mind maps using the Model Context Protocol (MCP). It leverages the open-source markmap project and provides users with diverse export formats including PNG, JPG, and SVG. Designed for easy integration with MCP clients, it offers tools for automated browser previews, rich interactivity, and batch mind map generation. The server can be installed easily via npm or Smithery and supports configurable output directories.

⭐ 137
MCP
jinzcdev/markmap-mcp-server

Mindmap MCP Server

Convert Markdown content into interactive mindmaps via an MCP-compliant server.

Mindmap MCP Server provides a Model Context Protocol (MCP) compatible service that transforms Markdown input into interactive mindmap visualizations. It supports command-line, Python, and Docker installation methods for flexibility across platforms. Designed to integrate with MCP clients like Claude Desktop, it ensures seamless Markdown-to-mindmap conversion using markmap under the hood. The server is intended for easy plug-and-play use in model-powered workflows that require structured, visual context formatting.

⭐ 205
MCP
YuChenSSR/mindmap-mcp-server

piapi-mcp-server

TypeScript-based MCP server for PiAPI media content generation

piapi-mcp-server is a TypeScript implementation of a Model Context Protocol (MCP) server that connects with PiAPI to enable media generation workflows from MCP-compatible applications. It handles image, video, music, TTS, 3D, and voice generation tasks using a wide range of supported models like Midjourney, Flux, Kling, LumaLabs, Udio, and more. Designed for easy integration with clients such as Claude Desktop, it includes an interactive MCP Inspector for development, testing, and debugging.

⭐ 62
MCP
apinetwork/piapi-mcp-server

Replicate Flux MCP

MCP-compatible server for high-quality image and SVG generation via Replicate models.

Replicate Flux MCP is an advanced Model Context Protocol (MCP) server designed to enable AI assistants to generate high-quality raster images and vector graphics. It leverages Replicate's Flux Schnell model for image synthesis and Recraft V3 SVG model for vector output, supporting seamless integration with AI platforms like Cursor, Claude Desktop, Smithery, and Glama.ai. Users can generate images and SVGs by simply providing natural language prompts, with support for parameter customization, batch processing, and variant creation.

⭐ 66
MCP
awkoy/replicate-flux-mcp

Sequa MCP

Bridge Sequa's advanced context engine to any MCP-capable AI client.

Sequa MCP acts as a seamless integration layer, connecting Sequa’s knowledge engine with various AI coding assistants and IDEs via the Model Context Protocol (MCP). It enables tools to leverage Sequa’s contextual knowledge streams, enhancing code understanding and task execution across multiple repositories. The solution provides a simple proxy command to interface with standardized MCP transports, supporting configuration in popular environments such as Cursor, Claude, VSCode, and others. Its core purpose is to deliver deep, project-specific context to LLM agents through a unified and streamable endpoint.

⭐ 16
MCP
sequa-ai/sequa-mcp

View all Alternatives

Didn't find tool you were looking for?

Search AI Tools

MCP Mermaid

Key Features

Use Cases

README

MCP Mermaid

✨ Features

🤖 Usage

🚰 Run with SSE or Streamable transport

Option 1: Global Installation

Option 2: Local Development

Access Points

🎮 CLI Options

🔨 Development

Start the MCP server

📄 License

Star History

Repository Owner

Repository Details

Programming Languages

Tags

Topics

Related MCPs