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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.