mcp_excalidraw and excalidraw-mcp
These are competitors—both provide MCP server implementations for programmatic Excalidraw diagram generation, with A offering a more mature implementation (1,525 stars) that includes Claude Code skill integration, while B appears to be an earlier or alternative implementation with minimal adoption.
About mcp_excalidraw
yctimlin/mcp_excalidraw
MCP server and Claude Code skill for Excalidraw — programmatic canvas toolkit to create, edit, and export diagrams via AI agents with real-time canvas sync.
Implements a persistent, programmatic canvas with 26 MCP tools for element-level CRUD operations, enabling AI agents to iteratively inspect and refine diagrams via `describe_scene` and `get_canvas_screenshot`. Syncs in real-time over WebSocket to a standalone Excalidraw instance, with fallback to REST API for environments without MCP support. Supports multi-agent concurrent editing, layout automation (`align_elements`, `distribute_elements`), file I/O, snapshots, and Mermaid conversion — differentiating it from stateless, one-shot diagram generation approaches.
About excalidraw-mcp
cmd8/excalidraw-mcp
Model Context Protocol server for Excalidraw diagrams
Exposes tools for programmatic diagram manipulation—creating nodes and edges, deleting elements, and retrieving full diagram state as markdown—enabling AI assistants to read and modify Excalidraw diagrams via stdio transport. Integrates with multiple MCP-compatible IDEs and editors (Cursor, Claude Desktop, VS Code, Windsurf) through standardized server configuration, operating on local `.excalidraw` files specified via CLI argument.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work