excalimaid
Converts Mermaid diagrams into Excalidraw diagrams, serves them locally, and opens the result in your browser.
README
Excalimaid
Converts Mermaid diagrams into Excalidraw diagrams, serves them locally, and opens the result in your browser. Includes an MCP server for AI assistants. All processing is done locally, no data is sent to external servers.
Installation
npm install -g excalimaid
Usage
CLI
Open a Mermaid diagram in Excalidraw:
excalimaid 'graph TD
A-->B'
Or pipe via stdin:
cat diagram.mmd | excalimaid
Tip
Add to your ~/.zshrc or ~/.bashrc to open whatever Mermaid diagram is in your clipboard:
alias mmd='pbpaste | excalimaid'
Then just copy a Mermaid diagram and run mmd.
MCP Server
Excalimaid provides an MCP server for AI assistants:
excalimaid mcp
Tool: open-diagram
Opens a Mermaid diagram in Excalidraw. Supports Flowchart, Sequence, and Class diagrams.
{
"name": "open-diagram",
"arguments": {
"mermaid": "graph TD\nA-->B"
}
}
Starts a local HTTP server on the default port 17532 (configurable via EXCALIMAID_PORT), opens your browser, and returns the URL.
The server auto-shuts down after 5 minutes of inactivity.
MCP Setup
Configure excalimaid in your MCP client:
OpenCode (opencode.json):
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"excalimaid": {
"type": "local",
"command": ["npx", "-y", "excalimaid@latest", "mcp"],
"enabled": true
}
}
}
Claude or Cursor
{
"mcpServers": {
"excalimaid": {
"command": "npx",
"args": ["-y", "excalimaid@latest", "mcp"]
}
}
}
Once configured, the open-diagram tool will be available to your AI assistant.
Configuration
| Variable | Description | Default |
|---|---|---|
EXCALIMAID_PORT |
Port for the local HTTP server | 17532 |
EXCALIMAID_IDLE_TIMEOUT |
Idle timeout in minutes before the server shuts down | 5 |
Example:
EXCALIMAID_PORT=8080 excalimaid 'graph TD
A-->B'
How it works
Made with the tool itself, obviously
- The script base64-encodes the Mermaid syntax and passes it as a
?mermaid=query parameter - It serves the
dist/directory via a minimal HTTP server on the default port 17532 - The React app decodes the parameter and converts it to Excalidraw elements using
@excalidraw/mermaid-to-excalidraw - The result is rendered in a full-screen Excalidraw canvas
Development
Clone and setup for local development:
git clone https://github.com/mklinovsky/excalimaid.git
cd excalimaid
pnpm install
pnpm run build
Link globally to use the local version:
pnpm link --global
Now you can run excalimaid from anywhere using your local build.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。