# excalidraw/excalidraw-mcp

Fast and streamable Excalidraw MCP App

Repository: https://github.com/excalidraw/excalidraw-mcp
Canonical: https://ross.abutalabs.com/products/excalidraw-mcp
Homepage: https://mcp.excalidraw.com
Language: TypeScript
License Family: other
Last push: 2026-03-24T12:27:09+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 73, release rhythm 69, longevity 15
- inputs: {"age_days": 210, "days_push": 162, "days_rel": 205, "gap_med": 1.0, "n_releases_24m": 5}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5183, forks 480 (observed 2026-08-28T04:09:11.829502+00:00)

## What it is
An MCP (Model Context Protocol) server that lets AI clients like Claude and ChatGPT generate and stream interactive hand-drawn Excalidraw diagrams with viewport camera control and fullscreen editing. It can be used remotely via a hosted endpoint or installed locally in Claude Desktop.

## Use cases
- draw diagrams from natural language prompts in Claude
- generate architecture diagrams with an AI assistant
- render interactive Excalidraw sketches inside chat apps
- self-host an MCP diagram server on Vercel
- create flowcharts and system diagrams via MCP

## When to choose
- you use an MCP-capable client and want AI-generated diagrams
- you want interactive, editable diagram output rather than static images
- you want a hosted or self-deployed MCP server with no configuration

## When to avoid
- your client does not support MCP or MCP Apps
- you need programmatic diagram generation outside of AI chat clients
- you need a general-purpose diagramming tool independent of LLMs

## Facets
- artifact type: service
- maturity: active
- function: mcp, chatbot, developer-tools
- domain: artificial-intelligence, developer-tools
- platform: self-hosted, cloud
- tags: mcp-server, excalidraw, mcp-apps, diagram-generation, streamable, vercel, diagramming, web-server, nodejs

## Member repositories
- excalidraw/excalidraw-mcp (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:11.829502+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:01:47.451706+00:00, confidence not recorded.
  - readme: https://github.com/excalidraw/excalidraw-mcp (fetched 2026-08-28T04:09:11.829502+00:00, sha 3b9ce83ae9ef)
- Data as of 2026-08-30T08:39:29.467469+00:00.