Skip to content
Back to search

excalidraw-mcp

Fast and streamable Excalidraw MCP App

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/excalidraw--excalidraw-mcp/badge.svg)](/listings/excalidraw--excalidraw-mcp)

HTML

<a href="/listings/excalidraw--excalidraw-mcp"><img src="/api/listings/excalidraw--excalidraw-mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Works with any client that supports [MCP Apps](https://modelcontextprotocol.io/docs/extensions/apps) — Claude, ChatGPT, VS Code, Goose, and others. If something doesn't work, please [open an issue](https://github.com/antonpk1/excalidraw-mcp-app/issues).

Remote (recommended)

`https://mcp.excalidraw.com`

For apps that don't yet have an official integration, you can add a custom MCP / connector (naming can vary between apps).

Local

**Option A: Download Extension**

1. Download `excalidraw-mcp-app.mcpb` from [Releases](https://github.com/antonpk1/excalidraw-mcp-app/releases) 2. Double-click to install in Claude Desktop

**Option B: Build from Source**

git clone https://github.com/excalidraw/excalidraw-mcp.git
cd excalidraw-mcp-app
pnpm install && pnpm run build

Add to `~/Library/Application Support/Claude/claude_desktop_config.json`:

{
  "mcpServers": {
    "excalidraw": {
      "command": "node",
      "args": ["/path/to/excalidraw-mcp-app/dist/index.js", "--stdio"]
    }
  }
}

Restart Claude Desktop.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 98 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Excalidraw MCP App Server
  2. MCP server that streams hand-drawn Excalidraw diagrams with smooth viewport camera control and interactive fullscreen editing.
  3. ![Demo](docs/demo.gif)
  4. ## Install
  5. Works with any client that supports [MCP Apps](https://modelcontextprotocol.io/docs/extensions/apps) — Claude, ChatGPT, VS Code, Goose, and others. If something doesn't work, please [open an issue](https://github.com/antonpk1/excalidraw-mcp-app/issues).
  6. ### Remote (recommended)
  7. ### `https://mcp.excalidraw.com`
  8. For apps that don't yet have an official integration, you can add a custom MCP / connector (naming can vary between apps).
  9. ### Local
  10. **Option A: Download Extension**
  11. 1. Download `excalidraw-mcp-app.mcpb` from [Releases](https://github.com/antonpk1/excalidraw-mcp-app/releases)
  12. 2. Double-click to install in Claude Desktop
  13. **Option B: Build from Source**
  14. ```bash
  15. git clone https://github.com/excalidraw/excalidraw-mcp.git
  16. cd excalidraw-mcp-app
  17. pnpm install && pnpm run build
  18. ```
  19. Add to `~/Library/Application Support/Claude/claude_desktop_config.json`:
  20. ```json
  21. {
  22. "mcpServers": {
  23. "excalidraw": {
  24. "command": "node",
  25. "args": ["/path/to/excalidraw-mcp-app/dist/index.js", "--stdio"]
  26. }
  27. }
  28. }
  29. ```
  30. Restart Claude Desktop.
  31. ## Usage
  32. Example prompts:
  33. - "Draw a cute cat using excalidraw"
  34. - "Draw an architecture diagram showing a user connecting to an API server which talks to a database"
  35. ## What are MCP Apps and how can I build one?
  36. Text responses can only go so far. Sometimes users need to interact with data, not just read about it. [MCP Apps](https://github.com/modelcontextprotocol/ext-apps/) is an official Model Context Protocol extension that lets servers return interactive HTML interfaces (data visualizations, forms, dashboards) that render directly in the chat.
  37. - **Getting started for humans**: [documentation](https://modelcontextprotocol.io/docs/extensions/apps)
  38. - **Getting started for AIs**: [skill](https://github.com/modelcontextprotocol/ext-apps/blob/main/plugins/mcp-apps/skills/create-mcp-app/SKILL.md)
  39. ## Contributing
  40. PRs welcome! See [Local](#local) above for build instructions.
  41. ### Deploy your own instance
  42. You can deploy your own copy to Vercel in a few clicks:
  43. 1. Fork this repo
  44. 2. Go to [vercel.com/new](https://vercel.com/new) and import your fork
  45. 3. No environment variables needed — just deploy
  46. 4. Your server will be at `https://your-project.vercel.app/mcp`
  47. ### Release checklist
  48. <details>
  49. <summary>For maintainers</summary>
  50. ```bash
  51. # 1. Bump version in manifest.json and package.json
  52. # 2. Build and pack
  53. pnpm run build && mcpb pack .
  54. # 3. Create GitHub release
  55. gh release create v0.3.0 excalidraw-mcp-app.mcpb --title "v0.3.0" --notes "What changed"
  56. # 4. Deploy to Vercel
  57. vercel --prod
  58. ```
  59. </details>
  60. ## Credits
  61. Built with [Excalidraw](https://github.com/excalidraw/excalidraw) — a virtual whiteboard for sketching hand-drawn like diagrams.
  62. ## License
  63. MIT

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.