excalidash-mcp

excalidash-mcp

MCP server that lets Claude (and other MCP clients) create, list, read, update, and delete drawings in ExcaliDash via its REST API. It allows users to create diagrams directly from natural language commands like 'draw a flowchart'.

Category
Visit Server

README

excalidash-mcp

MCP server that lets Claude (and other MCP clients) create, list, read, update, and delete drawings in ExcaliDash via its REST API.

End state: add one URL to your Claude config and say "畫個 XX 流程圖" — the drawing appears in your ExcaliDash dashboard.

Tools

  • create_drawing(name, elements?, appState?){ id, url, name }
  • update_drawing(id, elements, appState?)
  • list_drawings()Array<{ id, name, updatedAt, url }>
  • get_drawing(id){ id, name, elements, appState, url }
  • delete_drawing(id)

Element JSON is passed straight through to ExcaliDash — use the standard Excalidraw element format (type, x, y, width, height, etc.).

Endpoints

  • POST /mcp — Streamable HTTP MCP endpoint (stateless mode)
  • GET /health — JSON health check (also reports current authMode)

Environment

Var Required Default Notes
EXCALIDASH_URL yes https://excalidash.bamolab.org Base URL of the ExcaliDash backend (the same host that serves the frontend — the /api/... prefix is added automatically)
EXCALIDASH_API_KEY one of two An exd_... API key — generate in ExcaliDash → account → API keys. Must have drawings:read + drawings:write scopes
EXCALIDASH_EMAIL + EXCALIDASH_PASSWORD one of two Fallback email+password login (uses cookie session + CSRF)
PORT no 8080 HTTP listen port

The server fail-fasts on startup if no credentials are configured.

Prefer the API key path — it skips ExcaliDash's CSRF/cookie dance entirely because the backend treats Bearer requests without an Origin/Referer header as non-browser API requests (see backend/src/server/csrf.tsisNonBrowserApiKeyBearerRequest).

Claude Desktop / Claude Code config

{
  "mcpServers": {
    "excalidash": {
      "type": "http",
      "url": "https://excalidash-mcp.bamolab.org/mcp"
    }
  }
}

For Claude Code, the equivalent CLI:

claude mcp add --transport http excalidash https://excalidash-mcp.bamolab.org/mcp

Local development

npm install
npm run build
EXCALIDASH_API_KEY=exd_... npm start

Smoke-test the MCP surface:

curl -s -X POST http://localhost:8080/mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' | jq

License

MIT

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured