Skip to main content
Glama

Excalidraw MCP Server

by yctimlin
docker-compose.yml1.61 kB
version: '3.8' # Docker Compose for MCP Excalidraw # # Usage scenarios: # 1. Canvas only: docker-compose up canvas # 2. MCP only: docker-compose up mcp (requires canvas running elsewhere) # 3. Both: docker-compose --profile full up # # Most common: Run canvas locally, MCP via Claude Desktop config services: # Canvas server (optional) - Visual UI and REST API canvas: build: context: . dockerfile: Dockerfile.canvas image: mcp-excalidraw-canvas:latest container_name: mcp-excalidraw-canvas ports: - "3000:3000" environment: - NODE_ENV=production - PORT=3000 - HOST=0.0.0.0 - DEBUG=false restart: unless-stopped healthcheck: test: ["CMD", "node", "-e", "require('http').get('http://localhost:3000/health', (r) => process.exit(r.statusCode === 200 ? 0 : 1))"] interval: 30s timeout: 10s retries: 3 start_period: 40s networks: - mcp-network # MCP server - Core product (typically run via Claude Desktop, not docker-compose) # This is here for testing or special deployment scenarios mcp: build: context: . dockerfile: Dockerfile image: mcp-excalidraw:latest container_name: mcp-excalidraw-mcp stdin_open: true tty: true environment: - NODE_ENV=production - EXPRESS_SERVER_URL=http://canvas:3000 - ENABLE_CANVAS_SYNC=true - DEBUG=false depends_on: canvas: condition: service_healthy networks: - mcp-network profiles: - full networks: mcp-network: driver: bridge

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/yctimlin/mcp_excalidraw'

If you have feedback or need assistance with the MCP directory API, please join our Discord server